{ "complete": true, "report": { "bucket": "emo_Shame", "label": "Intense Shame", "definition": { "id": "emo_Shame", "category": "emotion", "head": "emo_Shame", "pole": "high", "label": "Intense Shame", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_shame/full-v2-sealed/sealed-selected", "mission": "emotion_shame", "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": 6.280750455856324, "genuineness": 4.445088782310486, "wer": 0.014538966385740579, "identity": 0.634317722916603, "voiceclap": 0.07103896083310246, "fitness": 0.5155843605653256, "steering_v2": 0.36274124954795134, "raw_target": 0.02603431336581707, "target_cdf": 0.36274124954795134, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.282656707763672, "genuineness": 4.430026273727417, "wer": 0.01248453695631115, "identity": 0.634317722916603, "fitness": 0.5200241943367713, "steering_v2": 0.37136709794009565 }, "none": { "n": 50, "ce": 6.2788442039489745, "genuineness": 4.460151290893554, "wer": 0.016593395815170008, "identity": null, "fitness": 0.5111445267938801, "steering_v2": 0.35411540115580703 } } } } ], "selected_wording": { "id": "manual-48b6c1c43c18", "general": "Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.", "inline": [ "Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.", "Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.", "Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance." ], "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": 4.0 }, "n": 20, "target_z": -0.3499023416728269, "target_raw": 0.02780109494924545, "ce": 5.886396765708923, "genuineness": 4.55159318447113, "identity": 0.5326253160834312, "wer": 0.012423245614035088, "valid_fraction": 1, "identity_delta": -0.04626332521438599, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": -0.3370117197386011, "target_raw": 0.034556057304143906, "ce": 5.833627700805664, "genuineness": 4.46592526435852, "identity": 0.601933442056179, "wer": 0.008742690058479531, "valid_fraction": 1, "identity_delta": 0.023044800758361815, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": -0.3499023416728269, "target_raw": 0.02780109494924545, "ce": 5.886396765708923, "genuineness": 4.55159318447113, "identity": 0.5326253160834312, "wer": 0.012423245614035088, "valid_fraction": 1, "identity_delta": -0.04626332521438599, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.3536132799059468, "target_raw": 0.025856483727693558, "ce": 6.108195900917053, "genuineness": 4.5603796482086185, "identity": 0.5990603774785995, "wer": 0.013613691090471275, "valid_fraction": 1, "identity_delta": 0.02017173618078232, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.3549804680502037, "target_raw": 0.025140047818422318, "ce": 5.9260108232498165, "genuineness": 4.580149126052857, "identity": 0.5514933682978154, "wer": 0.015789473684210527, "valid_fraction": 0.95, "identity_delta": -0.027395273000001906, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.3645507793727687, "target_raw": 0.020124999433755876, "ce": 6.046838784217835, "genuineness": 4.5970945119857785, "identity": 0.6257538497447968, "wer": 0.006066176470588235, "valid_fraction": 1, "identity_delta": 0.04686520844697952, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.3656250024881646, "target_raw": 0.01956208348274231, "ce": 6.12666265964508, "genuineness": 4.481301617622376, "identity": 0.5945349156856536, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.015646274387836456, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.36660155874553735, "target_raw": 0.019050347059965132, "ce": 6.09231059551239, "genuineness": 4.469690871238709, "identity": 0.5810343340039253, "wer": 0.010526315789473684, "valid_fraction": 0.95, "identity_delta": 0.0021456927061080933, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.36777343876629803, "target_raw": 0.018436256796121597, "ce": 6.165184545516968, "genuineness": 4.505464315414429, "identity": 0.6085351809859276, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.029646539688110353, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": -0.3425781206901435, "target_raw": 0.03163914382457733, "ce": 5.7821492671966555, "genuineness": 4.410696089267731, "identity": 0.513128538429737, "wer": 0.01067251461988304, "valid_fraction": 1, "identity_delta": -0.06576010286808014, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": -0.3370117197386011, "target_raw": 0.034556057304143906, "ce": 5.833627700805664, "genuineness": 4.46592526435852, "identity": 0.601933442056179, "wer": 0.008742690058479531, "valid_fraction": 1, "identity_delta": 0.023044800758361815, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": -0.343164065676853, "target_raw": 0.031332096084952354, "ce": 5.7266498565673825, "genuineness": 4.461845803260803, "identity": 0.5320516921579838, "wer": 0.024817251461988304, "valid_fraction": 0.95, "identity_delta": -0.04683694913983345, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": -0.345507815765716, "target_raw": 0.0301039207726717, "ce": 5.913600420951843, "genuineness": 4.499188256263733, "identity": 0.608604434132576, "wer": 0.009027777777777777, "valid_fraction": 1, "identity_delta": 0.02971579283475876, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": -0.3458007800836729, "target_raw": 0.029950401186943053, "ce": 5.8713057279586796, "genuineness": 4.441448700428009, "identity": 0.5624756276607513, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.016413013637065887, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.3465820310611661, "target_raw": 0.029541008919477463, "ce": 6.051008677482605, "genuineness": 4.621884846687317, "identity": 0.6089047938585281, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.030016152560710906, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": -0.34755859158396385, "target_raw": 0.02902927026152611, "ce": 5.8609802484512326, "genuineness": 4.503581476211548, "identity": 0.5554043605923653, "wer": 0.008187134502923975, "valid_fraction": 1, "identity_delta": -0.023484280705451964, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": -0.34853515779399497, "target_raw": 0.028517528623342513, "ce": 5.980318856239319, "genuineness": 4.576383471488953, "identity": 0.5764695093035698, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.0024191319942474367, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": -0.3495117197386011, "target_raw": 0.0280057892203331, "ce": 6.011493825912476, "genuineness": 4.573245549201966, "identity": 0.5862672664225101, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.007378625124692917, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.351757811500291, "target_raw": 0.026828788965940476, "ce": 6.121499872207641, "genuineness": 4.554417419433594, "identity": 0.6107948452234269, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.03190620392560959, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.35214843627813347, "target_raw": 0.026624093204736708, "ce": 6.0496186256408695, "genuineness": 4.598349690437317, "identity": 0.6192586898803711, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.040370048582553865, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.35644531452163375, "target_raw": 0.024372436851263047, "ce": 6.100451827049255, "genuineness": 4.556613969802856, "identity": 0.5690847218036652, "wer": 0.005572755417956656, "valid_fraction": 1, "identity_delta": -0.00980391949415207, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.3576171902769694, "target_raw": 0.02375834882259369, "ce": 6.16200749874115, "genuineness": 4.4687494993209835, "identity": 0.5749415040016175, "wer": 0.011019736842105263, "valid_fraction": 0.95, "identity_delta": -0.003947137296199799, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.35986328061685097, "target_raw": 0.022581349313259124, "ce": 6.06570258140564, "genuineness": 4.575755918025971, "identity": 0.5903605632483959, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.01147192195057869, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.3598632820386593, "target_raw": 0.022581348568201064, "ce": 6.104025959968567, "genuineness": 4.60776379108429, "identity": 0.5695165723562241, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.00937206894159317, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.360156249911137, "target_raw": 0.02242782711982727, "ce": 6.039293193817139, "genuineness": 4.525547647476197, "identity": 0.6164479628205299, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.037559321522712706, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.36240234451644354, "target_raw": 0.021250825375318527, "ce": 6.150887751579285, "genuineness": 4.462787175178528, "identity": 0.5810598775744438, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.002171236276626587, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.3629882831050156, "target_raw": 0.02094378098845482, "ce": 6.075829482078552, "genuineness": 4.603684329986573, "identity": 0.5827204614877701, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0038318201899528504, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.36347656194460615, "target_raw": 0.0206879124045372, "ce": 6.135598111152649, "genuineness": 4.495108795166016, "identity": 0.5857275165617466, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": 0.006838875263929367, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.3662109353895033, "target_raw": 0.01925504207611084, "ce": 6.152873420715332, "genuineness": 4.501071047782898, "identity": 0.5841073140501976, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.005218672752380371, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.3688476576162689, "target_raw": 0.01787334308028221, "ce": 6.105217361450196, "genuineness": 4.542179155349731, "identity": 0.565106806345284, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.013781834952533245, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.3695312488447807, "target_raw": 0.01751512661576271, "ce": 6.123088383674622, "genuineness": 4.473142695426941, "identity": 0.5745829455554485, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.004305695742368698, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.36953125026658906, "target_raw": 0.01751512587070465, "ce": 6.137385201454163, "genuineness": 4.528999447822571, "identity": 0.5669692248106003, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.01191941648721695, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.3731445330161525, "target_raw": 0.015621688216924667, "ce": 6.133810997009277, "genuineness": 4.515819716453552, "identity": 0.5733608275651931, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.005527813732624054, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": -0.3388671838788319, "target_raw": 0.03358375430107117, "ce": 5.764476752281189, "genuineness": 4.439565873146057, "identity": 0.5216486774384975, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.05723996385931969, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.3710937507997672, "target_raw": 0.01669634208083153, "ce": 6.19060115814209, "genuineness": 4.377119290828705, "identity": 0.5788886412978173, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": -0.36230469045469543, "target_raw": 0.021301998198032378, "ce": 6.182658410072326, "genuineness": 4.328793728351593, "identity": 0.5739323124289513, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0049563288688659664, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.3656249982227396, "target_raw": 0.01956208571791649, "ce": 6.206883573532105, "genuineness": 4.361742961406708, "identity": 0.5634141102433204, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": -0.015474531054496764, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.37041015814944706, "target_raw": 0.01705455929040909, "ce": 6.168361639976501, "genuineness": 4.387788558006287, "identity": 0.5785982221364975, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.0002904191613197327, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.366015625559837, "target_raw": 0.019357388615608217, "ce": 6.249932880401611, "genuineness": 4.395006003379822, "identity": 0.5780217316746712, "wer": 0.012803500846979107, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": -0.32818359492521343, "target_raw": 0.039182184040546415, "ce": 5.97718150138855, "genuineness": 4.3810731792449955, "identity": 0.599761166665703, "wer": 0.024749294184076794, "valid_fraction": 0.98, "identity_delta": 0.021739434991031883, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": -0.33763671909878734, "target_raw": 0.034228544235229495, "ce": 5.8869527816772464, "genuineness": 4.318187265396118, "identity": 0.5977948135137559, "wer": 0.026372106154714848, "valid_fraction": 1, "identity_delta": 0.019773081839084626, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": -0.3274999997156383, "target_raw": 0.039540402591228485, "ce": 5.862965936660767, "genuineness": 4.288062314987183, "identity": 0.5583475360274315, "wer": 0.02820816864295125, "valid_fraction": 1, "identity_delta": -0.019674195647239684, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.010136719383149024, "ci95_z": [ -0.02437500376779208, 0.004101565001494032 ], "language_deltas": { "en": 0.00878906461049674, "de": 0.009667972493354748, "fr": -0.02832031203346914, "nl": -0.016406249200232814, "es": -0.024414072785894646 }, "languages_improved": 2, "clear_gain": false, "delta_ce": 0.02398684501647949, "delta_genuineness": 0.030124950408935546, "delta_wer": -0.0018360624882364015, "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": -0.009453124173573905, "ci95_z": [ -0.024882811713562263, 0.008417969223195588 ], "language_deltas": { "en": 0.02441405856781133, "de": -0.0022460903398815735, "fr": -0.01904296716157351, "nl": -0.016015621578773696, "es": -0.03437500035545208 }, "languages_improved": 1, "clear_gain": false, "delta_ce": -0.09022871971130371, "delta_genuineness": -0.06288591384887696, "delta_wer": 0.0016228119706380576, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.03783203063462358, "ci95_z": [ 0.022675784135826604, 0.05167968569163752 ], "language_deltas": { "en": 0.008789067454113415, "de": 0.03261718743335273, "fr": 0.05439453088344005, "nl": 0.056249999289095826, "es": 0.03710936811311589 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.2727513790130615, "delta_genuineness": -0.01393282413482666, "delta_wer": 0.011945793337097685, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 4.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793034238.5445025, "example": { "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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.", "language": "de", "seed": 1702, "scale": 0.0, "cfg": 4.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "006f3979fc3a1adbc03d25977bc7bf8849025c87e1ffc9c169c6177b1ed1e5e1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d4ef9f3f5c325431025c6bf121daa5933e8f166c21c5f680044ef203153e8c57", "generation_seconds_batch": 22.66996895405464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 6.300607204437256, "genuineness": 4.8588056564331055, "identity": 0.7360477447509766, "hypothesis": "J'ai trouvé la 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_Shame/006f3979fc3a1adbc03d25977bc7bf8849025c87e1ffc9c169c6177b1ed1e5e1.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": "008fed8c28e687785cfbf9a919c943339c400da3d4e5695af6a9549600a6c994", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "df04ee8c68631bda3a08103f78d37cb18591ef3ccfa80bf44b9d2189333517e5", "generation_seconds_batch": 15.125540070934221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 5.967014789581299, "genuineness": 4.68307638168335, "identity": 0.8001429438591003, "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_Shame/008fed8c28e687785cfbf9a919c943339c400da3d4e5695af6a9549600a6c994.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "016579cbf00af662545d065da04db7e2f797f4655ddfe9c5ef5665fbcdfed5b2", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "59173e6c7bcb50f7333776028632a79c9ff0014b33fa684bf2103ca78e65fb46", "generation_seconds_batch": 20.655237835017033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03614245355129242, "target_z": -0.3339843698903763, "ce": 5.824047088623047, "genuineness": 4.632867813110352, "identity": 0.5931363701820374, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/016579cbf00af662545d065da04db7e2f797f4655ddfe9c5ef5665fbcdfed5b2.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "01b689c9ca103c865d71d50cc467fed9c6232250fb506f3ec57012b3789febb7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86755b571942a4eb79fef0b4b65e9653fdc6eb2cc0e605425ce31511152fa232", "generation_seconds_batch": 19.993616230087355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 5.990842819213867, "genuineness": 4.268857479095459, "identity": 0.5322771072387695, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/01b689c9ca103c865d71d50cc467fed9c6232250fb506f3ec57012b3789febb7.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "01d91f75e5a922816023496962eb1f0b6a7dcbec67f560406d73984aca6153a5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9523036cc5ad4b6d2559b7812e828f6a4839e4d3bda7cd497d2a9ba245183be8", "generation_seconds_batch": 22.737989112967625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.967014789581299, "genuineness": 4.645420074462891, "identity": 0.4883383810520172, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/01d91f75e5a922816023496962eb1f0b6a7dcbec67f560406d73984aca6153a5.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "9d213f86f8e92f0f4bd77ab8e74f9557e3374d298162e91d921c21bea7739104", "generation_seconds_batch": 14.88743120606523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.7556610107421875, "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_Shame/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "02094ddf5db3113d745222a6524c275d57dc943b8deb7b6da800a4cf6aa1652d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f24c5a2810409becd18caeacf52aa9349c3efb222bc5c214b299ebc18552f73b", "generation_seconds_batch": 22.507037086994387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.205295085906982, "genuineness": 4.256305694580078, "identity": 0.5004796981811523, "hypothesis": "The 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_Shame/02094ddf5db3113d745222a6524c275d57dc943b8deb7b6da800a4cf6aa1652d.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "02723323a177c5761091aa7aa0d57f25f9eec7063e43d739e53c98e3bb661d64", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "18b897804f37d76021d3bad241fadac6eb581ac8089f2e731796f9f7bdcac4b4", "generation_seconds_batch": 20.781591697013937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.23706579208374, "genuineness": 4.545003414154053, "identity": 0.7186417579650879, "hypothesis": "J'ai trouvé la 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_Shame/02723323a177c5761091aa7aa0d57f25f9eec7063e43d739e53c98e3bb661d64.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "02a2d9b0ae3c012fe5ee1c6deef142a06d3eb20a44c402df4fce11c32dc4d14c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4d1159e2a8e00a2a46f4bcf3ab84b85e532622245913c68148dc3c64f5d5695c", "generation_seconds_batch": 20.067210973007604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04842419922351837, "target_z": -0.31054688321982943, "ce": 5.919358730316162, "genuineness": 4.218649387359619, "identity": 0.6667361259460449, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/02a2d9b0ae3c012fe5ee1c6deef142a06d3eb20a44c402df4fce11c32dc4d14c.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "02f0ee5c9bf3712e4148b255899c8ee47ecb071fa15a965cbd27863aeff4bf52", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0d751faf94233bda121db9678abde142574ddf92a8c16cd26fa92613b0ba232e", "generation_seconds_batch": 23.500846144976094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.6978355050086975, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/02f0ee5c9bf3712e4148b255899c8ee47ecb071fa15a965cbd27863aeff4bf52.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "02f696734f5e286acb861955749bdb8e27e7e547f799cb546100ba28e3b69721", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c027bdea3b0edd70f515bfe2ece21c1229b86fbb0381c1b3c9ded97e50d80977", "generation_seconds_batch": 20.565472154063173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 5.847874641418457, "genuineness": 4.457139015197754, "identity": 0.4381587505340576, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/02f696734f5e286acb861955749bdb8e27e7e547f799cb546100ba28e3b69721.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "03af5f282b852b2fb36a2906ec4e46fc9f322a18316ee47efb97f8d54f35a636", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "aa01b2ec3a4e140112843944da4bbd71465bfca294d865d51a5d1131b2852426", "generation_seconds_batch": 20.546010551974177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.36129269003868103, "hypothesis": "The 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_Shame/03af5f282b852b2fb36a2906ec4e46fc9f322a18316ee47efb97f8d54f35a636.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "04119a188c60ab0258b6606c4d4a99fcd1f9c2350159b67986ed5435f6023513", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7c66dd44f8f08df9739b17319a2ecc5fe22c72d1b6a6257a4f5d44b9a639535f", "generation_seconds_batch": 23.555159265059046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 6.252951145172119, "genuineness": 4.425758361816406, "identity": 0.783403217792511, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/04119a188c60ab0258b6606c4d4a99fcd1f9c2350159b67986ed5435f6023513.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "0485f71a0b657fc4a5be5d3e91de7176e4aecea9202f405aca8675b5dfeb699a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "19c649e05c05e897517fcc5bb4d19cfef6a6502a1902d8e361b37a97d2304401", "generation_seconds_batch": 14.687219031038694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.125868320465088, "genuineness": 4.356721878051758, "identity": 0.35204148292541504, "hypothesis": "The 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_Shame/0485f71a0b657fc4a5be5d3e91de7176e4aecea9202f405aca8675b5dfeb699a.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "04c38f730060963a8024872f4b0cf42078915d9c370ca1c0d5e9407b5cd1c555", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "356f0fdbf2f442d05383cb7835e2b3654d60fbf7a793e208ee61d25d92c7bbbd", "generation_seconds_batch": 20.20866179605946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 5.704906940460205, "genuineness": 4.68307638168335, "identity": 0.7300300598144531, "hypothesis": "La puerta sigue abierta. Y dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/04c38f730060963a8024872f4b0cf42078915d9c370ca1c0d5e9407b5cd1c555.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "04d2ca5011217c50bd458cfe0e49941940ee2908dbc057bcb445064af2a375c1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "75dc88b8a234e5ed2c5fbcb5e06fff00563fef56c4fad6959e50c64983b08e65", "generation_seconds_batch": 20.144304884015583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 5.80021858215332, "genuineness": 4.250029563903809, "identity": 0.5502430200576782, "hypothesis": "J'ai trouvé la 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_Shame/04d2ca5011217c50bd458cfe0e49941940ee2908dbc057bcb445064af2a375c1.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "0517e2d12dd5c62344c8f898e24ab17fa9b09dd73c336777d22eb182d31c1f04", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "662a1d7e0eb5072bcf1cbb8df372c0350af9bdce466445e02d904ce83373add0", "generation_seconds_batch": 21.388651090906933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.062326908111572, "genuineness": 4.532451152801514, "identity": 0.7439027428627014, "hypothesis": "La porte 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_Shame/0517e2d12dd5c62344c8f898e24ab17fa9b09dd73c336777d22eb182d31c1f04.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "055faf24632e17b9cccaa5aba3bf1a33cd179dc3ecd05472e1dc28e55d3b0476", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "46eabd8ed92d5dae94065985311a9cb52e6a6c111ea599816bb276cc0f47c5ba", "generation_seconds_batch": 15.722941685002297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 5.808161735534668, "genuineness": 4.570107460021973, "identity": 0.47463521361351013, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/055faf24632e17b9cccaa5aba3bf1a33cd179dc3ecd05472e1dc28e55d3b0476.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": "05843d9a995a11b9f71c2a1cc37480fcfdaa4744fe3af4a63986b50960e48373", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "68ae45539a228b854609c7763c3f5192d1a79b9b1b61126459312e4238d7b6c6", "generation_seconds_batch": 15.398398222052492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053541600704193115, "target_z": -0.3007812495556849, "ce": 5.808161735534668, "genuineness": 4.645420074462891, "identity": 0.8574788570404053, "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_Shame/05843d9a995a11b9f71c2a1cc37480fcfdaa4744fe3af4a63986b50960e48373.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "05860e46ab3775dd1e7868b0e920f566fecd05ea6e7baf5c27441f11972750e8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5e2d263518a1964a35ac2cd7abf9c9c39a7f6a9d462a7de973a50cd3f64374dd", "generation_seconds_batch": 21.652236112044193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 6.054384231567383, "genuineness": 4.281409740447998, "identity": 0.6314915418624878, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/05860e46ab3775dd1e7868b0e920f566fecd05ea6e7baf5c27441f11972750e8.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "e12993760a137506d78a76c822f7d01450d71afad0a2e70d4858313e74451fa0", "generation_seconds_batch": 16.09166037698742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.395919322967529, "genuineness": 4.400654315948486, "identity": 0.6394492983818054, "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_Shame/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.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": "05b3b175e9efa210894462351698da62fdb2a3fce32a7c3204734e1d398d06d2", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c56e7d546840ef5a977f386a3eecb66a70b50f5e1cdf4d9b473a30f5372212a", "generation_seconds_batch": 20.238516484969296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05865900218486786, "target_z": -0.29101561589154035, "ce": 6.1020402908325195, "genuineness": 4.306513786315918, "identity": 0.4493204951286316, "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_Shame/05b3b175e9efa210894462351698da62fdb2a3fce32a7c3204734e1d398d06d2.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "05be45ca232ce293952b9a692a6d55dd1c162c5d98ba3bc856919326b5ee2669", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "db832a5c836d8cba2dcde6a7d396617e9f5c2d012db70df31592b8cf330d3647", "generation_seconds_batch": 20.035365622956306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07708162069320679, "target_z": -0.25585938588572005, "ce": 5.935244083404541, "genuineness": 4.306513786315918, "identity": 0.6505926847457886, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/05be45ca232ce293952b9a692a6d55dd1c162c5d98ba3bc856919326b5ee2669.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "060d6b9afcdc2ddf06f67fac90cdd60cf95d0e7bec1835187b6993c94de5f79c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "28cff7f96612f571b9d21a70da6cc982304dafb5e65285bcb336c9f68f846d3f", "generation_seconds_batch": 23.842584580997936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.3294782042503357, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/060d6b9afcdc2ddf06f67fac90cdd60cf95d0e7bec1835187b6993c94de5f79c.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": "061843f0cc48de4fbf853b0008d90fad095b31f1b6847720d3609e2bd298966a", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "5ec587411cc05e5e2d1dff1a9acbb813d31b3ba75eaaa5a0bc1a46b4aadff5ea", "generation_seconds_batch": 14.707422261941247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 5.8875885009765625, "genuineness": 4.344170093536377, "identity": 0.4589165449142456, "hypothesis": "The keys are on the kitchen table. Like checked the drawer and looked 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_Shame/061843f0cc48de4fbf853b0008d90fad095b31f1b6847720d3609e2bd298966a.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "067619ca77001ba1001cd60590fea21353841ea3ec3af29a57133b107a07a17a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8adbbd639530748d92f76289916e8fbc5ef63bbf707852602730e93db7f1dad3", "generation_seconds_batch": 20.246585681918077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.41180419921875, "genuineness": 4.758388519287109, "identity": 0.6298362016677856, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/067619ca77001ba1001cd60590fea21353841ea3ec3af29a57133b107a07a17a.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "0695c313f195b5ac4e0a9d1c3f06c012fcc19d08b5d7a40c37f4e79c5c102657", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "873d33748cca2d04c16ff0aa6ebf37c3852d7aa4802b62866f9d96081ed4b417", "generation_seconds_batch": 19.74090334493667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05251811444759369, "target_z": -0.30273438766298044, "ce": 6.070269584655762, "genuineness": 4.381826400756836, "identity": 0.5223251581192017, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0695c313f195b5ac4e0a9d1c3f06c012fcc19d08b5d7a40c37f4e79c5c102657.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "07313053a313da7a1da8fa6568b59d6becd11ee168c6f3fe69265b3659108b93", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5fb68431588ad6cb58f30fdfc56fda0700650469d174c711db6f64dc1347f5e1", "generation_seconds_batch": 17.151193268946372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 5.391171455383301, "genuineness": 4.519899368286133, "identity": 0.3433801531791687, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/07313053a313da7a1da8fa6568b59d6becd11ee168c6f3fe69265b3659108b93.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "0797acab5ba3040a885fa740dd593d19784943b57999127f977399eeb6d9d8b3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b24da229567d2c716814482dfb2189e20d76764b5fe53c6dda8e520396ec4e72", "generation_seconds_batch": 20.29315788799431, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.229123115539551, "genuineness": 4.921566009521484, "identity": 0.5600926876068115, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0797acab5ba3040a885fa740dd593d19784943b57999127f977399eeb6d9d8b3.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": "07da8e1d0da2efe0ffcdeeafb2171ada14d2a1b1c893b423764cff264f40e13c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "cf28296b14b1d27cadcb8cd28fbf9cbae549574b7f41d6c4fe163cd2d7816775", "generation_seconds_batch": 14.710344118997455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06275291740894318, "target_z": -0.2832031203346914, "ce": 5.689021587371826, "genuineness": 4.231201171875, "identity": 0.8049069046974182, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suche in der Schullade. Dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "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_Shame/07da8e1d0da2efe0ffcdeeafb2171ada14d2a1b1c893b423764cff264f40e13c.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "081de5f7f540270901cab8d2eaecb8aa4760a313083da42600a58376a4cf1480", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80f4d00c53a2670e3217ec214b182bac5909a4fe629e14c6ce3c205ceffb3c04", "generation_seconds_batch": 22.72839836694766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.673136234283447, "genuineness": 4.595211505889893, "identity": 0.5811646580696106, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/081de5f7f540270901cab8d2eaecb8aa4760a313083da42600a58376a4cf1480.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": "088a0ea9c1aa7c3fb432069f6df18cbf92532ddc847486772cf6af9d13520e5f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "f068b291b34ce49dc2b1147c46bda95d4ad1760ff1e576310e44f6082de6442f", "generation_seconds_batch": 15.698529572924599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 6.062326908111572, "genuineness": 4.080576419830322, "identity": 0.5789105296134949, "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_Shame/088a0ea9c1aa7c3fb432069f6df18cbf92532ddc847486772cf6af9d13520e5f.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": "08b013859fb37762dc54f7f11b2c1e9d357d4379a459659229362f085c9d2c61", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "41c771b62d4fef92066e76260375d9fb5601954363240a6e4126ae2a41cac258", "generation_seconds_batch": 15.798909601056948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 5.879645347595215, "genuineness": 4.256305694580078, "identity": 0.2309843897819519, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las 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_Shame/08b013859fb37762dc54f7f11b2c1e9d357d4379a459659229362f085c9d2c61.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": "08fdb0615016cd68e57a21203a082d6a3e9ebb61c970865a9d00be5e90e7886e", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90afcfcc4835e4b798a760985f9fe9ae4bb80cad46058a523174c8deef4d5410", "generation_seconds_batch": 14.610216099070385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0668468326330185, "target_z": -0.27539062477784243, "ce": 6.078212261199951, "genuineness": 4.557555198669434, "identity": 0.8248801231384277, "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_Shame/08fdb0615016cd68e57a21203a082d6a3e9ebb61c970865a9d00be5e90e7886e.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "0985b9fe3e3bd79778b4a18c54f06298f6ea7d43a6402d8001065fa4bffc0e2e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4cb0b23c45ffbf87a8e043f24413aefdc387892228594affbdfe496f5bd290e2", "generation_seconds_batch": 22.973680666065775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 6.078212261199951, "genuineness": 4.557555198669434, "identity": 0.5480065941810608, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0985b9fe3e3bd79778b4a18c54f06298f6ea7d43a6402d8001065fa4bffc0e2e.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "099cffa14c42830b7b1a4675d4df197a1fa5550138c15e28e318804dc0265d40", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "959bc5d2960e7ff033b88a88e116ae8311de9e0f7ef9bea7705153fe09d33517", "generation_seconds_batch": 14.7705800520489, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.125868320465088, "genuineness": 4.796044826507568, "identity": 0.3781132102012634, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/099cffa14c42830b7b1a4675d4df197a1fa5550138c15e28e318804dc0265d40.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": "09a95dc4d70d6c9832d1ad7f0b785152d4814e41c3fa9e15ac4b9aaadea87e71", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "e18a38f4a2da507dd0e7be9b9d34b3cd1e7320337be95e452d45536abfe3dba0", "generation_seconds_batch": 14.670312038972043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 5.49045467376709, "genuineness": 4.13078498840332, "identity": 0.8214452266693115, "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_Shame/09a95dc4d70d6c9832d1ad7f0b785152d4814e41c3fa9e15ac4b9aaadea87e71.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "09ae733289279d453a3e9cb65a3be4f9821a84a2568188043d281b722d4e9128", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ff1d433995aef26ff9699db67f9ee50ba79e77fccd5c9bd69287684d09e38c9c", "generation_seconds_batch": 20.478110032971017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 5.9431867599487305, "genuineness": 4.770940780639648, "identity": 0.5802515745162964, "hypothesis": "La porte 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_Shame/09ae733289279d453a3e9cb65a3be4f9821a84a2568188043d281b722d4e9128.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": "0a07cdd1a36b1e8c3ccac96aec0a4bacf88ccd98ec02d7d82084f3bdd727f1e8", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e73074e6c578e867a8dec813d330521f9c56c2c6c72972fb1e1bb42ffa216d2a", "generation_seconds_batch": 22.20848460996058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 5.831989288330078, "genuineness": 3.9801597595214844, "identity": 0.3430655002593994, "hypothesis": "The keys are on the kitchen table. Check the drawer then looked 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_Shame/0a07cdd1a36b1e8c3ccac96aec0a4bacf88ccd98ec02d7d82084f3bdd727f1e8.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": "0a15d2b1d784005317f328c1a8a918ee1b4d6816a701ceb34545255f26b5d7f2", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5f8adcbd424fb6ca50bbab86b945a40f6f8ab4a20f4741cc09c4658bcf6c38f", "generation_seconds_batch": 21.370640140026808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 5.982900142669678, "genuineness": 4.482243061065674, "identity": 0.6650906801223755, "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_Shame/0a15d2b1d784005317f328c1a8a918ee1b4d6816a701ceb34545255f26b5d7f2.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "0a41c4e2f1826d3471279f1b10f30f7fd39210202017aae2dc08df0b539faa5e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "70ce9025e66ad0ad97b58eebdcd82f18e8af108970d62f6c85223c2e1931e616", "generation_seconds_batch": 17.00375408900436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0017262846231460571, "target_z": -0.40624999644547916, "ce": 6.125868320465088, "genuineness": 4.65797233581543, "identity": 0.5112041234970093, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0a41c4e2f1826d3471279f1b10f30f7fd39210202017aae2dc08df0b539faa5e.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "0af5edb5447eb6356ed23da455fd5e0ff77659d0951b63d4750d4a959c09eabe", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b79b5b3c35debddee3205052d21c55b89007f392ac8183f94ffc7744503f27f2", "generation_seconds_batch": 20.441806128947064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.0146708488464355, "genuineness": 4.18099308013916, "identity": 0.5128628015518188, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0af5edb5447eb6356ed23da455fd5e0ff77659d0951b63d4750d4a959c09eabe.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "0b4485a81b9d34e2416561b5a5afd37acd7d4cc6cc65aefd0ed5a541a69786da", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7ea6d96746679e021627c0fb4ede16413263e7e3324cbaff06bf062441b0a4d7", "generation_seconds_batch": 21.35962164599914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06377638876438141, "target_z": -0.2812500106635625, "ce": 6.23706579208374, "genuineness": 4.595211505889893, "identity": 0.6611014604568481, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0b4485a81b9d34e2416561b5a5afd37acd7d4cc6cc65aefd0ed5a541a69786da.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "0b7081b1718561524af61465228e658417db6e4a32d985113f57a9228bde7c3c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dd56e1260ec8697a6914e4400b4dbc52cdde797d6cbcabd2fd3071845b94db50", "generation_seconds_batch": 23.709746224922128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.6535776853561401, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0b7081b1718561524af61465228e658417db6e4a32d985113f57a9228bde7c3c.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "0c0ef66b3c1b761b63d6274bae8af5ad9c3a8292e43417d6c33184fa41dade05", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a91f6494a9e6be72de85072985998535f4ae6556fc939f9a9ee0df60fc2acd35", "generation_seconds_batch": 20.179360706009902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 6.181467056274414, "genuineness": 4.557555198669434, "identity": 0.4872167408466339, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0c0ef66b3c1b761b63d6274bae8af5ad9c3a8292e43417d6c33184fa41dade05.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "0c4cbf3f045f67a9d30a255b45223b2933964d397870f242056b62a2cfcbef31", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "47abb6d6d597080c5302712dc1683c757d6d6660ed295cc04e434810db74dac9", "generation_seconds_batch": 20.04080380103551, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 6.125868320465088, "genuineness": 4.6705241203308105, "identity": 0.652786135673523, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0c4cbf3f045f67a9d30a255b45223b2933964d397870f242056b62a2cfcbef31.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "0c5a5024853325b777fbb755f431511a7143c950db7fe75039e21949cedd77f8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "323512f2388d4d8d27ee5a418ba5c538446323dc2d91a361b4fbe12d5f39882b", "generation_seconds_batch": 19.957515476970002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.443574905395508, "genuineness": 4.68307638168335, "identity": 0.6018358469009399, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0c5a5024853325b777fbb755f431511a7143c950db7fe75039e21949cedd77f8.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": "0c95b77d5ddc5409678d6562fcc4e09ec53600fecbc6f5c92ad88c04fc62804d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "97a1bac1f0e6c3ab1d2f3e26b5477ba4033a8fcb4213d250786d12397be717a6", "generation_seconds_batch": 18.09070794598665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07912857830524445, "target_z": -0.2519531381072956, "ce": 5.974957466125488, "genuineness": 4.093128204345703, "identity": 0.45762062072753906, "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_Shame/0c95b77d5ddc5409678d6562fcc4e09ec53600fecbc6f5c92ad88c04fc62804d.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "080a0ff9b1ba37e7feca6504ec8152b94c07b5d2ad00cb63eaef13a625c6a5d3", "generation_seconds_batch": 14.847838882007636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0058201998472213745, "target_z": -0.41406249200232814, "ce": 6.062326908111572, "genuineness": 4.325342178344727, "identity": 0.8594228625297546, "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_Shame/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "0d38d2262bc6419538bfad910104cd8260e61f16043f9a0bb2dea8ccd99ff0fe", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4b0ac8ac680afab8ebb0b5a9d21b316218b157792d4c10cf9d63537a8adede76", "generation_seconds_batch": 22.39894927898422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 5.919358730316162, "genuineness": 4.319066047668457, "identity": 0.6746751070022583, "hypothesis": "The 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_Shame/0d38d2262bc6419538bfad910104cd8260e61f16043f9a0bb2dea8ccd99ff0fe.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": "0da911eb48b23933ffbf5916a466c0f44b98beff74cbe6136bf4cde1c6589b52", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2a19ea3bfeb9642822422df5e957aad386f8248cc055d33b3b0e57e8d6d6b09e", "generation_seconds_batch": 20.05306732398458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 5.95112943649292, "genuineness": 4.432034492492676, "identity": 0.6924737691879272, "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_Shame/0da911eb48b23933ffbf5916a466c0f44b98beff74cbe6136bf4cde1c6589b52.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "0ddb380b9f3d4dbd35caca1f9b0dfeca82065afea9f592eec0694ea128b57368", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0fb017320e0d5debf34e2760e36b4a8a8fa3f18270547bbb73761fd2ee2f40cf", "generation_seconds_batch": 21.388651090906933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0017262846231460571, "target_z": -0.40624999644547916, "ce": 6.09409761428833, "genuineness": 4.833701133728027, "identity": 0.6648275852203369, "hypothesis": "La porte 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_Shame/0ddb380b9f3d4dbd35caca1f9b0dfeca82065afea9f592eec0694ea128b57368.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "0dfb66e2cc927b047ee3f5953e92d263eefbd7f55f31df506e7884040d58c2e9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38b797cb866544bea17b5db5137f16da3d4dc23d2ce38abfb01fefde8b8fcde4", "generation_seconds_batch": 20.951461654971354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 6.2767791748046875, "genuineness": 4.256305694580078, "identity": 0.5586893558502197, "hypothesis": "The 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_Shame/0dfb66e2cc927b047ee3f5953e92d263eefbd7f55f31df506e7884040d58c2e9.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "0e3e2cf686fa06ec8630b55f7d713e14cbc1e7a9703b6284f67ad457b819f560", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1b54c9e901116cfbfa365de5a8e7f7691bc423706fd1a165598644a8fca06dac", "generation_seconds_batch": 21.86258301208727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.181467056274414, "genuineness": 4.846253395080566, "identity": 0.7404934167861938, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0e3e2cf686fa06ec8630b55f7d713e14cbc1e7a9703b6284f67ad457b819f560.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "0e53133d5456716b506effef8b9c3e51a6fddac8ff46aabdfe97ec5370462032", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2725876312a4b25fa9d1f93c019cdfde99ff0c5f9b8f99ced0de74f31923fbe3", "generation_seconds_batch": 19.63655632501468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 5.959072113037109, "genuineness": 4.036643981933594, "identity": 0.2445080280303955, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd: Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/0e53133d5456716b506effef8b9c3e51a6fddac8ff46aabdfe97ec5370462032.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": "0e9e31858ce6c700b8cc631120aca6915b3820b292e8869e4bfcd8d5109584d4", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "3448c71936b7955091ecc013a3ac1cfd36369ed71ccbf1ed3c407c359ac4e6b8", "generation_seconds_batch": 14.832779667922296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05251811444759369, "target_z": -0.30273438766298044, "ce": 5.569881439208984, "genuineness": 4.507347106933594, "identity": 0.7491137385368347, "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_Shame/0e9e31858ce6c700b8cc631120aca6915b3820b292e8869e4bfcd8d5109584d4.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "0ed01f127c85af7fe68e035564106769d1aa2d6cf8dd1fd583d9bdd8ccde7690", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b7def18b0c5af5f3b1fc20f470e41e057083fe8dab4df2a8ce9c86a98545ce6b", "generation_seconds_batch": 24.023545506992377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 5.744620323181152, "genuineness": 4.507347106933594, "identity": 0.7102004289627075, "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_Shame/0ed01f127c85af7fe68e035564106769d1aa2d6cf8dd1fd583d9bdd8ccde7690.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": "0f220076932c55e8792f33397e7df19dc2b25981ebc13a30396252550019a0be", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "86570b2f425bf0b394649e83052b4af6c600114ccfdb5f90c7ee3fb16c33f573", "generation_seconds_batch": 14.846746501047164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015031516551971436, "target_z": -0.43164062122332164, "ce": 5.831989288330078, "genuineness": 4.482243061065674, "identity": 0.7390919327735901, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, liese genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "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_Shame/0f220076932c55e8792f33397e7df19dc2b25981ebc13a30396252550019a0be.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "0f531d69e040bcc8471e201d77c9ddbf3e19772d5429542526abdfb26d8d2174", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "86e8289867e512cb6760c034392afca0974dd2eb3e588500771839774ce8f374", "generation_seconds_batch": 21.563719175057486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 5.935244083404541, "genuineness": 4.7332844734191895, "identity": 0.684088408946991, "hypothesis": "J'ai trouvé la 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_Shame/0f531d69e040bcc8471e201d77c9ddbf3e19772d5429542526abdfb26d8d2174.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "0fb04dd87786e1c8ddd2695e1aa5e2581761e7be5f4c8d26a88cb3f9ae66ae7c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "eb5521c213c9980a90472e0a0a92564fb836f1c56e61a23163778a2b3122dee7", "generation_seconds_batch": 20.73968642600812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.8875885009765625, "genuineness": 4.6705241203308105, "identity": 0.8221343755722046, "hypothesis": "J'ai trouvé la 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_Shame/0fb04dd87786e1c8ddd2695e1aa5e2581761e7be5f4c8d26a88cb3f9ae66ae7c.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "0fd169fbc182f112e882893db848f420375b94d5a2ebac12d44d64da30461cad", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "80fed86809d9981cae3c3b8400af35bfe476c5bb0c09afa67b594ef5852d5c07", "generation_seconds_batch": 20.38845843600575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.2767791748046875, "genuineness": 4.400654315948486, "identity": 0.6256036162376404, "hypothesis": "The 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_Shame/0fd169fbc182f112e882893db848f420375b94d5a2ebac12d44d64da30461cad.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": "104209ee09937b23b06593e98d452cfc4de6bb0458910e825b5097c871e91e63", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a123f53f6d75f4e8b73de112e1360322e787f82c6ad3b9d25398d9c6f1dd3b79", "generation_seconds_batch": 14.783872278989293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.213237762451172, "genuineness": 4.137060642242432, "identity": 0.32202643156051636, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/104209ee09937b23b06593e98d452cfc4de6bb0458910e825b5097c871e91e63.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "106d1bbc64146b57e4051f4c99d74afb1e599fd524965b5ed46ce548eeb27dce", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "eb0897072a14a34788f047825c9fc0534f5aff1e0548d951201cdf24c3bc0f3c", "generation_seconds_batch": 20.90892271406483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.292664527893066, "genuineness": 4.545003414154053, "identity": 0.5675467252731323, "hypothesis": "La porte 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_Shame/106d1bbc64146b57e4051f4c99d74afb1e599fd524965b5ed46ce548eeb27dce.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "10832de8446328b6a5215c4af4925ac580dbfa79ea716498bdafc8c0b6d15a8b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bd04a290124bead661c58f4cb9afddfc59b860ddd0e479257435ad759992f870", "generation_seconds_batch": 20.91753686789889, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 6.1894097328186035, "genuineness": 4.519899368286133, "identity": 0.7722188234329224, "hypothesis": "La porte 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_Shame/10832de8446328b6a5215c4af4925ac580dbfa79ea716498bdafc8c0b6d15a8b.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "10f0ed003334d2d291bc49e98dafd55f568f47c31e6e107059b250029be6612b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "99dbcacdb75119853d4a26c8a3370901d40f12900749b237516f16e6565a6ceb", "generation_seconds_batch": 15.722941685002297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0058201998472213745, "target_z": -0.41406249200232814, "ce": 6.038498878479004, "genuineness": 4.494794845581055, "identity": 0.6478180885314941, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/10f0ed003334d2d291bc49e98dafd55f568f47c31e6e107059b250029be6612b.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "91390804c4b495bd8a32140888079ee68459231270381a4be1abe5d4c5aba180", "generation_seconds_batch": 14.85626734001562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.213237762451172, "genuineness": 4.13078498840332, "identity": 0.5201380252838135, "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_Shame/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "12f71ab023ff8d6b105052cd5e65106f1285b5d04a754d0b5e82f2b98632d87d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5e296e1cf5db3429aa10bf7dd7c321a517d0ee089fcccd7a4b8985c7a9c74ec0", "generation_seconds_batch": 20.237323093926534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 6.046441555023193, "genuineness": 4.68307638168335, "identity": 0.7338097095489502, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/12f71ab023ff8d6b105052cd5e65106f1285b5d04a754d0b5e82f2b98632d87d.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "132eca1a717cbca255157469ac48e375398204d2a7b0468a5a5ca10b69cf788d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "af5b650f19af2e5d3e5ff0e36ded87f2d7835883f44f937a6d0d261b5ffd9cb2", "generation_seconds_batch": 15.584855855093338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 6.117925643920898, "genuineness": 3.9927117824554443, "identity": 0.44703227281570435, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/132eca1a717cbca255157469ac48e375398204d2a7b0468a5a5ca10b69cf788d.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": "13a027a6ef2f1d6d4a7a851b7401e09ab0275bf18426ce5fc2592c4c8b044704", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "c02957d192267808c408850d9d6106e0916715a6954f84efbc9bb4c512e1331c", "generation_seconds_batch": 15.987172010005452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055588558316230774, "target_z": -0.2968750017772604, "ce": 5.895530700683594, "genuineness": 4.331617832183838, "identity": 0.5591228604316711, "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_Shame/13a027a6ef2f1d6d4a7a851b7401e09ab0275bf18426ce5fc2592c4c8b044704.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "13e185c647206bb5b53319cfb923e04f29da4d69d5181feb9f9376cc733d2353", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "286a83ad1322ffae4e065918726e6e22b3aeb0f54f97cc11718e5e3ec32f6315", "generation_seconds_batch": 19.972217981005087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 6.09409761428833, "genuineness": 4.770940780639648, "identity": 0.7778017520904541, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/13e185c647206bb5b53319cfb923e04f29da4d69d5181feb9f9376cc733d2353.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "14149a26d3f625651d0690244df901946d95e96a9337455afc064b64a0f07b2f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8b45f12135a27b7981615830dbca76da2ae5e4de5edb12e35b2941449e5ef89f", "generation_seconds_batch": 22.187535247998312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 5.792276382446289, "genuineness": 4.3504462242126465, "identity": 0.7656842470169067, "hypothesis": "J'ai trouvé la 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_Shame/14149a26d3f625651d0690244df901946d95e96a9337455afc064b64a0f07b2f.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": "143195d689e6934edd8602dc9fc7603daea1618ef107eb9ee415ae8341cff6af", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "46105cc3f2cfad8905a0795c29822fc222920bf554e8762b6218b380436e90d4", "generation_seconds_batch": 14.529730711015873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06787031888961792, "target_z": -0.2734374866705469, "ce": 5.367343425750732, "genuineness": 4.005263805389404, "identity": 0.43975257873535156, "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_Shame/143195d689e6934edd8602dc9fc7603daea1618ef107eb9ee415ae8341cff6af.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "143e86362ad76cb9a27c1c4ab179b8f6cdf1c3334bbc1a12c28f9d26fc4ed23e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fba444b0dc6fbb28687991ddd209d77705a2638d89687ff053222173f77efb15", "generation_seconds_batch": 20.29315788799431, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 6.268836498260498, "genuineness": 4.8588056564331055, "identity": 0.6291511654853821, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/143e86362ad76cb9a27c1c4ab179b8f6cdf1c3334bbc1a12c28f9d26fc4ed23e.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "1445f1533c494298cbc47ca79e49197daa29f8faa562a1ea94b903ab1d457812", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8a5971eed81e9eef67971fe07bc544c0c7b9f4d40af52f2cb8acef683463132c", "generation_seconds_batch": 24.17110184300691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.41180419921875, "genuineness": 4.65797233581543, "identity": 0.44592422246932983, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1445f1533c494298cbc47ca79e49197daa29f8faa562a1ea94b903ab1d457812.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "146a8f29cf2b528d4ab75531b35b0204ead8cb9d56b5afd16190713886eb722f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ba7a6814e9a9f54325dd21ca1b9f8b81400c55badcbd2def51a2a1c26cd4d4e6", "generation_seconds_batch": 20.011510295094922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.054384231567383, "genuineness": 4.645420074462891, "identity": 0.7739113569259644, "hypothesis": "J'ai trouvé la 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_Shame/146a8f29cf2b528d4ab75531b35b0204ead8cb9d56b5afd16190713886eb722f.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "9d16cd16706e0fd036addf0ff3ffdc0dcae9cd44debd2ae2f986091c2f0e3310", "generation_seconds_batch": 15.993559505906887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.316492557525635, "genuineness": 4.419482707977295, "identity": 0.5776058435440063, "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_Shame/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.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": "15e49ea3879991d4c554c7041af96c985c3efe556eea339fc9186282a1aa151a", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "5361d7426f973696abb785dcd2602a347ea4364e016a5eb33f28b0796b6b2484", "generation_seconds_batch": 15.011670393054374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.23706579208374, "genuineness": 4.250029563903809, "identity": 0.2587915062904358, "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_Shame/15e49ea3879991d4c554c7041af96c985c3efe556eea339fc9186282a1aa151a.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": "15f8eba5950873e794df9e131d39fadf6f3673486bfc8f383a5bf1d37fd61a0c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "38ccd224a0a00f265478d803eb3ebe015991fd521148b01bd1c74d2612d58126", "generation_seconds_batch": 14.901888021966442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.3336523473262787, "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_Shame/15f8eba5950873e794df9e131d39fadf6f3673486bfc8f383a5bf1d37fd61a0c.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "1638b8525f5c7dd9e3be340e2e8b606c465fada688e124e6d3b56f75816b466c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "033c860399b8f2c2be287b0540a35cea04dbd503689253ff77ed0d2e4cf017e2", "generation_seconds_batch": 22.14649874099996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.0146708488464355, "genuineness": 4.319066047668457, "identity": 0.8518905639648438, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1638b8525f5c7dd9e3be340e2e8b606c465fada688e124e6d3b56f75816b466c.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "167bf95fbd35f586caf56413f98d3869e029e24fe1041817f02f15a7bd2d33ef", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c21d21ba5eba9393ea4a2e7f41805df8c191b85baf477df5facc73597269c603", "generation_seconds_batch": 20.85800313600339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05865900218486786, "target_z": -0.29101561589154035, "ce": 6.157639026641846, "genuineness": 4.65797233581543, "identity": 0.6010040044784546, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/167bf95fbd35f586caf56413f98d3869e029e24fe1041817f02f15a7bd2d33ef.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "1784361e9e5560a499c34721c401f855a04bf98f2e38e5aba8b8ceb8808743d6", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "af6d0ffd3d4490b9d06e915ef09a52bc9f8730004c6ae9ec5391160585000269", "generation_seconds_batch": 20.25057317991741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 6.117925643920898, "genuineness": 4.482243061065674, "identity": 0.728714108467102, "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_Shame/1784361e9e5560a499c34721c401f855a04bf98f2e38e5aba8b8ceb8808743d6.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "180e4f9ccc8301b599fbfe335d0929e52c482437335b7c50289fa82d5ce62f0f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6553c606e260ae5084cc8b1228fffb989bdc8e9e894e4d16eafe455b9635510d", "generation_seconds_batch": 21.9075062579941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.09409761428833, "genuineness": 4.3127899169921875, "identity": 0.3986119031906128, "hypothesis": "The 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_Shame/180e4f9ccc8301b599fbfe335d0929e52c482437335b7c50289fa82d5ce62f0f.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "182187ce81b0e35a95dfe607749e0a7d7917a573236551b04de2d4cf413ba264", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8b7a16c384b2201644371a10ce86dcb29d0536d0ef721bc10b4c61a0ea455633", "generation_seconds_batch": 21.19603384693619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006843686103820801, "target_z": -0.4160156301096237, "ce": 6.149696350097656, "genuineness": 4.444586753845215, "identity": 0.5671223402023315, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/182187ce81b0e35a95dfe607749e0a7d7917a573236551b04de2d4cf413ba264.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "191bd632b5acbb49cf15ee83c1ac5164015290a90fb58e0274a1eaec343ee5f7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7dd07eb9d130a1b03e0bafb7b5dbad4efc68701933fe351393a398b2ef5a72cb", "generation_seconds_batch": 21.241799412993714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 5.967014789581299, "genuineness": 4.6203155517578125, "identity": 0.5863784551620483, "hypothesis": "J'ai trouvé la 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_Shame/191bd632b5acbb49cf15ee83c1ac5164015290a90fb58e0274a1eaec343ee5f7.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "19784dc6147abf6fb3399ccbbb09f747eddcea8de1360501e4f0ba3b15c7b16e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d499a157701fb8729f1a1792a4a9587325a32494eb904196f553db0a64840ca", "generation_seconds_batch": 15.22024724201765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.1894097328186035, "genuineness": 4.68307638168335, "identity": 0.6810823678970337, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/19784dc6147abf6fb3399ccbbb09f747eddcea8de1360501e4f0ba3b15c7b16e.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "19fd5697e695651564be059263506e9c406c5c511780c800ea121ea44308b844", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5f920f321ea9fbf0c3d9f0a7167bf06e1662a532f7e294ad7b3e154be92b1978", "generation_seconds_batch": 21.08082812698558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055588558316230774, "target_z": -0.2968750017772604, "ce": 5.95112943649292, "genuineness": 4.2374773025512695, "identity": 0.40965771675109863, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/19fd5697e695651564be059263506e9c406c5c511780c800ea121ea44308b844.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "1b1da294e0c2da8f048efe9375378265309e0164c78cb126f32cc17bdbeccca3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0f18f7f6ee434e06b7e2a1533c85bc8cd5e3f8532d94979a460e24b94feaa3b2", "generation_seconds_batch": 20.102902905084193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 5.744620323181152, "genuineness": 4.595211505889893, "identity": 0.7530432939529419, "hypothesis": "La porte 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_Shame/1b1da294e0c2da8f048efe9375378265309e0164c78cb126f32cc17bdbeccca3.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": "1b39777a04c814178df01bc0cbb3b00c5990caae2f2254415b31479061ad098d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b276c3d86ae4f4d3ac850bf7c61ba68dee55de10c294128eb002ab491cf9093e", "generation_seconds_batch": 14.331568472087383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09755121171474457, "target_z": -0.21679687966530858, "ce": 6.086154937744141, "genuineness": 4.281409740447998, "identity": 0.6236242651939392, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1b39777a04c814178df01bc0cbb3b00c5990caae2f2254415b31479061ad098d.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "1b720f3be60788d3bbc9f16d68a10722435e5b1ba50db7d0c108ea5e31fda253", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b7ee33aad237a8a8935c3965aa8f4671353ea65c58bc6183f2c20f0d99f404fb", "generation_seconds_batch": 20.90328396402765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009914115071296692, "target_z": -0.4218749875591771, "ce": 6.173524379730225, "genuineness": 4.808597087860107, "identity": 0.763697624206543, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1b720f3be60788d3bbc9f16d68a10722435e5b1ba50db7d0c108ea5e31fda253.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "1bb933db32548c8a1b6be46389de4ffff0bc3eaa2acf44cf3e61cc3b986cd811", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "23e6b5d4f7c41c9a2f5a9ff6102685eae2b3e237f0bc1cd99b788659ab0f7db0", "generation_seconds_batch": 20.46953083400149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.09409761428833, "genuineness": 4.381826400756836, "identity": 0.5361074209213257, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1bb933db32548c8a1b6be46389de4ffff0bc3eaa2acf44cf3e61cc3b986cd811.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": "1beb3f8b6d063157b980c5241e9b06d7ee1f3b8c9b4495a98b9812412c347235", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5f506f8ff5fcd30ad92e054403552be93dc39f8244ba47106db4698d65c98ddb", "generation_seconds_batch": 15.675206494983286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 5.871703147888184, "genuineness": 4.607763767242432, "identity": 0.6257489919662476, "hypothesis": "Quelqu'un a déplacé la petite chasse bleue, elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1beb3f8b6d063157b980c5241e9b06d7ee1f3b8c9b4495a98b9812412c347235.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "1befb40eb24d6ec324727d67e058c2f4861176b4edd614b74ecaa99510fc83fd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b5e05cc3d5bcf0cef194b46229bd1c66d9ea3cb9bca022d231c273991ea4e302", "generation_seconds_batch": 20.0596611360088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 5.95112943649292, "genuineness": 4.432034492492676, "identity": 0.620943009853363, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1befb40eb24d6ec324727d67e058c2f4861176b4edd614b74ecaa99510fc83fd.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "1c60049cc43bd0f3747001db27c28d3267e96ec22a38ffb2ee0a751d1d72d0ed", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a30e8c29d7ffbcd5fc00cba36917139c25e476a51db50ea7f214feda0b6372b9", "generation_seconds_batch": 14.917726065963507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 5.967014789581299, "genuineness": 4.519899368286133, "identity": 0.7680124044418335, "hypothesis": "J'ai trouvé la 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_Shame/1c60049cc43bd0f3747001db27c28d3267e96ec22a38ffb2ee0a751d1d72d0ed.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "1c703708bfa7a4078474683e6cbc790e44d751aab3186daa0240ac558f4e95a9", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "dae3e62c8e772b150b5e8de8f92f8da04376db864e2474517a91dc4810db32bd", "generation_seconds_batch": 18.104903239989653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 5.919358730316162, "genuineness": 4.6203155517578125, "identity": 0.7104133367538452, "hypothesis": "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_Shame/1c703708bfa7a4078474683e6cbc790e44d751aab3186daa0240ac558f4e95a9.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": "1d28275d68286cefb830ac2fa22f9ad6088431242ca4b2164e7b498574ef600a", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "a085e367b7cd0e0a45442b39a049ac6f419d7fbb7817ea795eef46842ee88a61", "generation_seconds_batch": 14.474077310995199, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 5.557967185974121, "genuineness": 4.256305694580078, "identity": 0.39546293020248413, "hypothesis": "De sleutels liggen op de keukentafel. Ik in de la en daarna naast het raam neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1d28275d68286cefb830ac2fa22f9ad6088431242ca4b2164e7b498574ef600a.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "fca06e696346b70e72294ec627e2166b6ea5e51280d806e999362be5396c3aff", "generation_seconds_batch": 17.07926029106602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.117925643920898, "genuineness": 4.381826400756836, "identity": 0.638862133026123, "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_Shame/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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "dbe43cce7dabadae6bce371e305dc065de8d65af8ff7a49cc8110f05cb6ff238", "generation_seconds_batch": 16.606683464953676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.109982967376709, "genuineness": 4.413206577301025, "identity": 0.445515900850296, "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_Shame/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "1ddcbca799938a3df558efaacaae2f808e9fa7c017d713ce12bce32d2470b77b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "780958c3215d6e0ac5ac8515cd34232924b184cbf0a6d0d582d272a63e42ed7f", "generation_seconds_batch": 20.478110032971017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 6.054384231567383, "genuineness": 4.7332844734191895, "identity": 0.7856962084770203, "hypothesis": "La porte 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_Shame/1ddcbca799938a3df558efaacaae2f808e9fa7c017d713ce12bce32d2470b77b.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": "1e49e7e410dc858a35cf06f99d8261ef978df8d698e43cd3e8c7e4d05321e0c6", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "b51653c73b785e2eb82fdc2000a989bc08283e244e29d5604f08cb54a268ef30", "generation_seconds_batch": 14.852508100913838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05047115683555603, "target_z": -0.30664063544140496, "ce": 5.95112943649292, "genuineness": 4.18099308013916, "identity": 0.35612067580223083, "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_Shame/1e49e7e410dc858a35cf06f99d8261ef978df8d698e43cd3e8c7e4d05321e0c6.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": "1e83bc2cfeebd54584cc7c838636bf45356f337df5c843338230d84810219ad8", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e195004859a63941b3f7a8f7193cdc936f38a6de1b3ad31333b32d837349003b", "generation_seconds_batch": 21.264940754976124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 6.117925643920898, "genuineness": 4.545003414154053, "identity": 0.7717256546020508, "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_Shame/1e83bc2cfeebd54584cc7c838636bf45356f337df5c843338230d84810219ad8.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": "1e98e1e7994a4c1dc5ce0ef283b7d6040f5511e16b7a9161ac1fd5727d5fd984", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3c2d7bdd796c2652c2b9428622eb9fb335e0f03ac4af59074ecc100da2f7f7a0", "generation_seconds_batch": 21.752503636991605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 5.728734970092773, "genuineness": 4.137060642242432, "identity": 0.4604017734527588, "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_Shame/1e98e1e7994a4c1dc5ce0ef283b7d6040f5511e16b7a9161ac1fd5727d5fd984.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "1e9b528e6ba814ed13bc4f7bd0be585edad3dd28bebc9d6da531b7a5ce9c7e94", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bf98ce6a0518756f9eab79974bc299f63361d4ebcc2e7902a8ba01513d68f856", "generation_seconds_batch": 16.91590196802281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 5.6413655281066895, "genuineness": 4.582659721374512, "identity": 0.5240746736526489, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1e9b528e6ba814ed13bc4f7bd0be585edad3dd28bebc9d6da531b7a5ce9c7e94.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "b8bea28660c932ce2fd5d4d39c755d117df8f3b608e38a24b32314c153ca03f0", "generation_seconds_batch": 17.07926029106602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.340320587158203, "genuineness": 4.532451152801514, "identity": 0.6835300922393799, "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_Shame/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "1ee015673824e6d77b7b228f2a96e1a4e3aa8c7bc648cac840a2342cab276cc7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e375015c34abd464dc46e9d33799341436c8c5f745a3b74d5d7418b4c63830ea", "generation_seconds_batch": 20.06424557499122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 6.1020402908325195, "genuineness": 4.6956281661987305, "identity": 0.3974229693412781, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/1ee015673824e6d77b7b228f2a96e1a4e3aa8c7bc648cac840a2342cab276cc7.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": "1f0217eb5fe882dff812e6c921deff4e361f153773eb1793b08389bed3907c71", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "1443affe85e9d8e5c2a61b67682896e845f6af87bcb9fb45922f3dce3f2cf4a6", "generation_seconds_batch": 14.492139465990476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0811755508184433, "target_z": -0.24804686189270442, "ce": 5.855817794799805, "genuineness": 4.65797233581543, "identity": 0.5335620641708374, "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_Shame/1f0217eb5fe882dff812e6c921deff4e361f153773eb1793b08389bed3907c71.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "1fd74f2fa083159fd4d3928149f1eef43b24a8c713dcece81ec0c4322bc08ae0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6f063e4ab1ed325d936973598418e1fe748c29a408fda9abf47191e1e6ab3244", "generation_seconds_batch": 21.178151143016294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 5.375286102294922, "genuineness": 4.68307638168335, "identity": 0.5561884045600891, "hypothesis": "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_Shame/1fd74f2fa083159fd4d3928149f1eef43b24a8c713dcece81ec0c4322bc08ae0.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "2010b7ed0f78aef5632820e23efa48c51e9922189e6b55defae05b890342f057", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7c9cd963be4afb203151dadfa05200953a27fb06b5b602e53636a2d05e5b6db2", "generation_seconds_batch": 17.79290491808206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007485032081604004, "target_z": -0.38867186722448566, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.6378017663955688, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2010b7ed0f78aef5632820e23efa48c51e9922189e6b55defae05b890342f057.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "20407ef204ab97f683627d76886da353e2250d4c10280cbd4dbd02c3fb75613d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "35cdf1ad1842fe3d26e1e03039e40ac63e90f78d0c0b1de2109a3d5316721b3b", "generation_seconds_batch": 20.781591697013937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 6.086154937744141, "genuineness": 4.796044826507568, "identity": 0.7979552745819092, "hypothesis": "J'ai trouvé la 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_Shame/20407ef204ab97f683627d76886da353e2250d4c10280cbd4dbd02c3fb75613d.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "211bf393e67841cab96f50c836080f3b0491329cbc9645c7630652aa660df85e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e9ff16b2174cdb9809ccf40e2915fdec12e810662639276577ee493729f88991", "generation_seconds_batch": 16.76211588201113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.6559793949127197, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/211bf393e67841cab96f50c836080f3b0491329cbc9645c7630652aa660df85e.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "211edf04855bb2c93d1a237290f7c2aab159436292971177153d7b25ee502d33", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "49d3986b9bb660061bb045687550342e13a7ef677c13c57a4bd935d9963e0d59", "generation_seconds_batch": 23.061181511962786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0883399024605751, "target_z": -0.23437499466821876, "ce": 5.879645347595215, "genuineness": 4.369274139404297, "identity": 0.6792277097702026, "hypothesis": "J'ai trouvé la petite boîte, les débreis 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_Shame/211edf04855bb2c93d1a237290f7c2aab159436292971177153d7b25ee502d33.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "21ca18cc3b54b67608347cc4fe7b834cf8e37192d66748e7486a60945a281b1c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3074742136020712c3e29ccfce7fd262834c3422e748606fb20b12635e2e6dd1", "generation_seconds_batch": 16.945818534004502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 6.117925643920898, "genuineness": 4.042920112609863, "identity": 0.32996106147766113, "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_Shame/21ca18cc3b54b67608347cc4fe7b834cf8e37192d66748e7486a60945a281b1c.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": "21cdc7488c14124432b94f573c3d952607f9188f5abc0bc775ee618a7937269c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd5cd53f986543944e7ba27f7548b399bc58e8326b63401b91c118da09463c5d", "generation_seconds_batch": 17.745785551029257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 5.7684478759765625, "genuineness": 4.369274139404297, "identity": 0.46806246042251587, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed. Controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/21cdc7488c14124432b94f573c3d952607f9188f5abc0bc775ee618a7937269c.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "22059d851655248c8941f128ed91aa9dfef45393897a15127bff3f9dea97d189", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "32af73e9094105be504806093ad4519d5f3a853a22f3e34e8210a1934a8ef302", "generation_seconds_batch": 20.125160275027156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 6.022613525390625, "genuineness": 4.7081804275512695, "identity": 0.7727457880973816, "hypothesis": "J'ai trouvé la 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_Shame/22059d851655248c8941f128ed91aa9dfef45393897a15127bff3f9dea97d189.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "23316994710dd3c54f6f679820b5bad27cd8158b2033c232814eeb6c2c1b3148", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c2e1c85f1eb26d81880a766abe9eff9628e34a72289ae3cd47c5615dd031773b", "generation_seconds_batch": 22.776562015060335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 6.221180438995361, "genuineness": 4.432034492492676, "identity": 0.14940567314624786, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/23316994710dd3c54f6f679820b5bad27cd8158b2033c232814eeb6c2c1b3148.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "23e87c5127bf14f9c0ad27c5c9c385bcb8fef0fa30eb46ea757b464a976d2c00", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "37053500b3c31f9dc47ba483dafdda18705c7e8f58201ec37fe3b98f0781da51", "generation_seconds_batch": 19.928718034992926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.062326908111572, "genuineness": 4.494794845581055, "identity": 0.4575262665748596, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/23e87c5127bf14f9c0ad27c5c9c385bcb8fef0fa30eb46ea757b464a976d2c00.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "23fa9d66a26e5e4d8e29707737375289241d28c66dd3f97a222bbdf14fa77fda", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8cfde4a8dd3f879990cc1473689bd2e8a386b50710038a4d1845b4c90e4559bc", "generation_seconds_batch": 20.203011045930907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.6792066693305969, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/23fa9d66a26e5e4d8e29707737375289241d28c66dd3f97a222bbdf14fa77fda.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "2415f4955bf24f9cdf9810f227bcc40c8ccdc1b96fd08a5b4a8cc667c3606930", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e466d5a22ebe76b9fe93a769cc50bf3c0571dbcee0a884a18509c6376c206089", "generation_seconds_batch": 20.25545775797218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.173524379730225, "genuineness": 4.921566009521484, "identity": 0.6245005130767822, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2415f4955bf24f9cdf9810f227bcc40c8ccdc1b96fd08a5b4a8cc667c3606930.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "2500cc7a256fc56f45188271e49b3d3121a27e33355fd011a78c418b63fd52fd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f4cb25bf15b0e43935e9ef2e0bf8b54d2089ae854d482ea3e22f142139436b7e", "generation_seconds_batch": 21.636593889910728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.38797664642334, "genuineness": 4.65797233581543, "identity": 0.4453185796737671, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2500cc7a256fc56f45188271e49b3d3121a27e33355fd011a78c418b63fd52fd.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "259b9619e9b6dd292a9eb4f176787cc489283f812909d60772a97fadbb455fd7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7725bd87c4051e5623b12832d2ef250e193cc8c5713812f45bdb2d54b3115d96", "generation_seconds_batch": 15.172503227018751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 5.6532793045043945, "genuineness": 4.582659721374512, "identity": 0.6083976030349731, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/259b9619e9b6dd292a9eb4f176787cc489283f812909d60772a97fadbb455fd7.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "25bdfe6989d75d381facc87d2056cb204e8aabeea3460d76240a5a12f48e6b6e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d897607f8914f4bc0ad9cf4d26cda20614b38d945520391fe54052905bdeb5d7", "generation_seconds_batch": 20.06424557499122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 6.292664527893066, "genuineness": 4.7834930419921875, "identity": 0.4476661682128906, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/25bdfe6989d75d381facc87d2056cb204e8aabeea3460d76240a5a12f48e6b6e.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "2614dc2f0c761ff264839066fc4d68ce7695125ce4e264485656cb976f3c047a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "303a3ca5bbf25849816742faf1169c2cadb3af14d45ddef586ca3ae9f7c19aa6", "generation_seconds_batch": 20.065488351974636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.507116317749023, "genuineness": 4.469690799713135, "identity": 0.4887010455131531, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2614dc2f0c761ff264839066fc4d68ce7695125ce4e264485656cb976f3c047a.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "2615944ab396d2dac3f887d4ee4924e06ee22836c4d9154d51462dcf80a8ec77", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "774df9f06b8a561060955271c775f1c18be130bd83c990233adda5099c8398cc", "generation_seconds_batch": 21.726405469933525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456508696079254, "target_z": -0.29882811144838933, "ce": 6.054384231567383, "genuineness": 4.7458367347717285, "identity": 0.6848840713500977, "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_Shame/2615944ab396d2dac3f887d4ee4924e06ee22836c4d9154d51462dcf80a8ec77.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "2617b6c53b8e8244639c8af396180ef0d2beea29d57877606f391fd2f1f519f3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a3e0a7fe64e1a0610b071ec6f9c92d6cb4dd8db2431971aa840005336236e14d", "generation_seconds_batch": 15.22024724201765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04637724161148071, "target_z": -0.3144531309982539, "ce": 6.23706579208374, "genuineness": 4.7081804275512695, "identity": 0.431953489780426, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2617b6c53b8e8244639c8af396180ef0d2beea29d57877606f391fd2f1f519f3.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "26425312e32e1200afcc694a08c6d3ac334dc12bbd6d085697fb3a391d531cf5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bfd53122385978f43dd5cb412d78b0d8243f2cd4b73de2d4cdc9391792796388", "generation_seconds_batch": 21.818518418003805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 5.911416053771973, "genuineness": 4.369274139404297, "identity": 0.24899357557296753, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/26425312e32e1200afcc694a08c6d3ac334dc12bbd6d085697fb3a391d531cf5.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "266b5024250fadd17a66791d3ac5b31fa569c1e3e41009f0daf0a9f0deac9c3c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eee6f424b9ff28089613daa285cd570280d37e0ac78ab60a36701fec813e962d", "generation_seconds_batch": 22.11171580501832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044330283999443054, "target_z": -0.31835937877667836, "ce": 5.903473377227783, "genuineness": 4.080576419830322, "identity": 0.177274689078331, "hypothesis": "The 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_Shame/266b5024250fadd17a66791d3ac5b31fa569c1e3e41009f0daf0a9f0deac9c3c.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "26987d513a4ef743174859b65924e3701402651901ecc5c9d24e6d5598cef61e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3f5e17052d68713d68e9d7462377a6ae2716b28fa3bb84dc446b24e01547bda8", "generation_seconds_batch": 19.99357511207927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 5.919358730316162, "genuineness": 4.6203155517578125, "identity": 0.7660861015319824, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/26987d513a4ef743174859b65924e3701402651901ecc5c9d24e6d5598cef61e.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "147cc120e164cc2c107cf8535975f14d6e35d85556f7534c1fe440f496ef6858", "generation_seconds_batch": 15.107786376960576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 6.427689552307129, "genuineness": 4.337893962860107, "identity": 0.1380419284105301, "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_Shame/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.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": "27542ea01ad4e05fb2701b9d50338789c6d995393c8c5287f1075e1d8148f72e", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2edd9fe19ed89b337e669765b6847d0a576ff2e49692b88acd2f4b742b9dc19", "generation_seconds_batch": 15.687068126979284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 5.903473377227783, "genuineness": 4.532451152801514, "identity": 0.5172690153121948, "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_Shame/27542ea01ad4e05fb2701b9d50338789c6d995393c8c5287f1075e1d8148f72e.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": "2796dbb7898a480dbf0970d619b02075237801498832a3cd968e813565af4f0d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33bd5b7b7631ed14463012b37ab5adcebd63a7136d8094ae523b1eed8b28c2ab", "generation_seconds_batch": 20.23152689996641, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 5.689021587371826, "genuineness": 4.168440818786621, "identity": 0.7059803009033203, "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_Shame/2796dbb7898a480dbf0970d619b02075237801498832a3cd968e813565af4f0d.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "27d87bb4772930f2946baa6c39b3692c50f6f906c90bd76407ad1e9065546a9e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "15824b651bb4633b157ee710f246ec743f33be0ce2422301ec4309ef939e9d9a", "generation_seconds_batch": 20.249362161033787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 6.0305562019348145, "genuineness": 4.381826400756836, "identity": 0.15732379257678986, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/27d87bb4772930f2946baa6c39b3692c50f6f906c90bd76407ad1e9065546a9e.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "282967cd8ff1b22d231d8cb67d9ad070b336ada7f1c61e28e9e7df0232ea5492", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6f06a90943eac17ce5ba7b64e46c0a93a9f41c50276992e38d6c5486efbbc7aa", "generation_seconds_batch": 21.563719175057486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 5.696964263916016, "genuineness": 4.545003414154053, "identity": 0.6646103262901306, "hypothesis": "J'ai trouvé la 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_Shame/282967cd8ff1b22d231d8cb67d9ad070b336ada7f1c61e28e9e7df0232ea5492.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "282c5e6998995214ea4bfa55f3d5592627fcb74dc0d60863a5464c7bd12af665", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a470da902f56995c17e36c831b3f85fc518d0aef01dde905b461a6132e74846d", "generation_seconds_batch": 20.102902905084193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03447762131690979, "target_z": -0.4687499893364375, "ce": 5.736677646636963, "genuineness": 4.632867813110352, "identity": 0.5994267463684082, "hypothesis": "La porte 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_Shame/282c5e6998995214ea4bfa55f3d5592627fcb74dc0d60863a5464c7bd12af665.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "2845a5796e5975c4f8165dc91abefc8cecc1d5b7a56d841b0442102869b4b74e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "92da948519cd9003923efac272736e3240327152c6d8f43b8c05f3139c099492", "generation_seconds_batch": 16.61384928401094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.133810997009277, "genuineness": 4.7834930419921875, "identity": 0.7187478542327881, "hypothesis": "J'ai trouvé la 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_Shame/2845a5796e5975c4f8165dc91abefc8cecc1d5b7a56d841b0442102869b4b74e.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "29163ba4d8e2ed88750eded39f9c84edde9fc0f4e3722589c02592ac024892e5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cac71105fa224bc2ba955590816175b80e7d2f5a7fc210c0f7319db3a93d0c0c", "generation_seconds_batch": 14.801435771980323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.197352409362793, "genuineness": 3.986435890197754, "identity": 0.3465036153793335, "hypothesis": "The 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_Shame/29163ba4d8e2ed88750eded39f9c84edde9fc0f4e3722589c02592ac024892e5.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "29a16242060cbcb5da5e3bf2dc129e7cd270af4484a498e32b7ddff843f0d3f6", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1cf3a2df14c0291b1062b0553636c74b4ad7659f7db4ac3d92eb49d796422753", "generation_seconds_batch": 24.51609165093396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 5.855817794799805, "genuineness": 4.821148872375488, "identity": 0.7019407153129578, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du wenn du bereit bist.", "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_Shame/29a16242060cbcb5da5e3bf2dc129e7cd270af4484a498e32b7ddff843f0d3f6.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "2a1d632b8ad65159009f082733d91e59172f27af99eca7f1dc21b0d0d95227a8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "37d3058c04561c7c8bec4af8f13e7b584497fb6ceb880fcdd7b71804fadf6d20", "generation_seconds_batch": 19.924603677005507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 6.205295085906982, "genuineness": 4.3504462242126465, "identity": 0.6553291082382202, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2a1d632b8ad65159009f082733d91e59172f27af99eca7f1dc21b0d0d95227a8.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "2b3fd1524f08bc4ff0e08515bc4d76ae37da2184d2769707ce42a57cbf76bd14", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f76013dabc98976b3b1bd439e12aba7faab6b3d2c204b19e1e9c2c5153d7b6cd", "generation_seconds_batch": 19.9634273420088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.95112943649292, "genuineness": 4.595211505889893, "identity": 0.7485915422439575, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2b3fd1524f08bc4ff0e08515bc4d76ae37da2184d2769707ce42a57cbf76bd14.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "2b70a49e729d35469ed767bbb543a0a88a8d1b27998b6bc37eb28f24c5bbec71", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2eda256187fb6c64850e85f06346540256133f984cba3806b01341d4ecb496db", "generation_seconds_batch": 18.137261481955647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 6.054384231567383, "genuineness": 4.099404335021973, "identity": 0.38150742650032043, "hypothesis": "The 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_Shame/2b70a49e729d35469ed767bbb543a0a88a8d1b27998b6bc37eb28f24c5bbec71.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "2c35b2063ea0723f50aef3e41e78be34c34084e348fdbd865b11fa69e8d0f229", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "977d1fc6fb95441c104fcbb462e351d35b5c641b70365ed929165d4d1c8067a8", "generation_seconds_batch": 24.023545506992377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02014891803264618, "target_z": -0.44140625488746615, "ce": 5.728734970092773, "genuineness": 4.808597087860107, "identity": 0.6855005025863647, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise tais-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_Shame/2c35b2063ea0723f50aef3e41e78be34c34084e348fdbd865b11fa69e8d0f229.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": "2c6a9dbb30b91c9360710b1ca27c21507913194a26eaa9f7b248dce837b0824a", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "5b7f59fbdaee6ad1848c4fc6fa156f9f74145bcea1e5b4b75eccdcc59b5e95e6", "generation_seconds_batch": 14.852508100913838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.5559353828430176, "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_Shame/2c6a9dbb30b91c9360710b1ca27c21507913194a26eaa9f7b248dce837b0824a.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "2cb13c023714e85c739ae15526a1b7ce06ae712df207e7a732cb5e23967c0a9d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d1c8ff7370ca1f6b7024b3d8f4604f05699b932716042e30a3b87afec64b8a7b", "generation_seconds_batch": 20.233576430939138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06377638876438141, "target_z": -0.2812500106635625, "ce": 6.046441555023193, "genuineness": 4.111956596374512, "identity": 0.6507866978645325, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2cb13c023714e85c739ae15526a1b7ce06ae712df207e7a732cb5e23967c0a9d.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "2cc22887c4bfc612b7d645d90aa035f2de5090bc6687f2ccd1aaba3f1065cf51", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c572735e248d0ea26234ed1ffa49f20b9ad507fa730ba2b404bdf91561472c1f", "generation_seconds_batch": 23.842584580997936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.197352409362793, "genuineness": 4.7081804275512695, "identity": 0.31706300377845764, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2cc22887c4bfc612b7d645d90aa035f2de5090bc6687f2ccd1aaba3f1065cf51.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "2cf0a2cfdfbca9c5afb947877368758d982a750f89aa6cdf20535eaf7e7820e0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "55d40d96651a85110b5779a11ce9a6cf389536fdebfb5e2df8f44612f9680520", "generation_seconds_batch": 19.746941662044264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 6.284721851348877, "genuineness": 4.394378662109375, "identity": 0.2814098000526428, "hypothesis": "The 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_Shame/2cf0a2cfdfbca9c5afb947877368758d982a750f89aa6cdf20535eaf7e7820e0.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "2d685514bee49fbe9edb80f53fc8e3b7d2d796fd4e99b4c80224bdb498296cb5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "36467a001d4ea41614bc34d8f7c20594e53c9e63a19e033b3b778c9282f4c346", "generation_seconds_batch": 15.671517529990524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.308549880981445, "genuineness": 4.720732688903809, "identity": 0.39692676067352295, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2d685514bee49fbe9edb80f53fc8e3b7d2d796fd4e99b4c80224bdb498296cb5.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": "2db35ef7c4a770a530ccbe195b6fd9acf1e144a4f12a41f7e155f311f51963fc", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47306ba5d26a45f9146c67748010db25634d81f88928aebc66b11a0087bbfe24", "generation_seconds_batch": 20.25409739499446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 5.80021858215332, "genuineness": 4.2751336097717285, "identity": 0.36428168416023254, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk in Allah. En daarna naast het raam neem ze mee als je weggaat.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2db35ef7c4a770a530ccbe195b6fd9acf1e144a4f12a41f7e155f311f51963fc.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "2e336c8cbd58b3525f5f4bf88021e8dd3c38ed96e7fa021332b72e95882e3440", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "675f48edb409c0d8fc52cf670dfcfa760ad60b6a0e224ce6b5351d6c5e425472", "generation_seconds_batch": 14.791730290045962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 6.229123115539551, "genuineness": 4.720732688903809, "identity": 0.6021738052368164, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2e336c8cbd58b3525f5f4bf88021e8dd3c38ed96e7fa021332b72e95882e3440.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "2e7427bfa20b9f35fe497acb0a940c7ad7b8cb94ed16dc161ce7263cd5b22968", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e97a8e03ba89fe9857cad0c7c0993530cd3602bc97336512ef4a69c8073b6792", "generation_seconds_batch": 20.206565120024607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.403861999511719, "genuineness": 4.344170093536377, "identity": 0.23701360821723938, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2e7427bfa20b9f35fe497acb0a940c7ad7b8cb94ed16dc161ce7263cd5b22968.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "2ee22f5bb95d16235e2878cec26f5916f00de2611768931a62d36e79d20079d0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "be2c951a6ed573d206e00dcc8b8961cf8953a167aa39ee72f3e21148e2a80ab6", "generation_seconds_batch": 23.01182540995069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 5.927301406860352, "genuineness": 4.582659721374512, "identity": 0.6374648213386536, "hypothesis": "La porte 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_Shame/2ee22f5bb95d16235e2878cec26f5916f00de2611768931a62d36e79d20079d0.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "2ef4ea4b6e581c98d7e45afe25ba05145fc8817cb7120de27756f1de6d35b427", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "24a151fe6dce1c8e2c932f7b42d601dd867cc74b7b118564d3ae3e4df6ecc43a", "generation_seconds_batch": 22.196229992085136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 5.839932441711426, "genuineness": 4.507347106933594, "identity": 0.2567988634109497, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2ef4ea4b6e581c98d7e45afe25ba05145fc8817cb7120de27756f1de6d35b427.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": "2f53119da319e79098992ee1192d30ee2b9509fa6d83bca2715eea63e2d61ca1", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "88829fa692e6d8ebb0c29d949d882adeda35254a02cf688e45847b06f5022bd3", "generation_seconds_batch": 22.96394300099928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 6.1894097328186035, "genuineness": 4.287685871124268, "identity": 0.6568359732627869, "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_Shame/2f53119da319e79098992ee1192d30ee2b9509fa6d83bca2715eea63e2d61ca1.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": "2f897bc8cbab9aa3c096995d4f52f90ad3841e6e2b2ba638636a0e639fb473bb", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "df6efb3f49619b17e30233ab07ea34238de217d97b42ff01993347f5923ce5bb", "generation_seconds_batch": 15.125540070934221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042283326387405396, "target_z": -0.3222656265551029, "ce": 6.046441555023193, "genuineness": 4.482243061065674, "identity": 0.5363022685050964, "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_Shame/2f897bc8cbab9aa3c096995d4f52f90ad3841e6e2b2ba638636a0e639fb473bb.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "2fd959547f8bc4e74955818f8a5966b3a5477f7dee8ba82948444990dfd816af", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "abaf29a469a4ff1eee600c6f1aa56691a8bed413af78e412444cef2dbb189517", "generation_seconds_batch": 20.33966451708693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 5.71682071685791, "genuineness": 4.400654315948486, "identity": 0.580981433391571, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2fd959547f8bc4e74955818f8a5966b3a5477f7dee8ba82948444990dfd816af.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "2ff40bcc7d9ef0c5915cbacb52c06ca7496b0f4f691fab9ae418f58687c0b4d3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c9953df1391d07584eeef9f508756ab14b6f6e1d4d60c33f15beb820c0a96704", "generation_seconds_batch": 19.864949120092206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.459460258483887, "genuineness": 4.570107460021973, "identity": 0.685921311378479, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster, wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/2ff40bcc7d9ef0c5915cbacb52c06ca7496b0f4f691fab9ae418f58687c0b4d3.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": "30380da1f02a0a36dda778e661f70c63633e16ec702b75e7bcb3da751fdddfa2", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "687f11aece4f3f7d23ee917868ae3d42d018d1d2e8c7fedc9d46d11bb5f03407", "generation_seconds_batch": 14.76605577103328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044330283999443054, "target_z": -0.31835937877667836, "ce": 5.831989288330078, "genuineness": 4.3504462242126465, "identity": 0.5659768581390381, "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_Shame/30380da1f02a0a36dda778e661f70c63633e16ec702b75e7bcb3da751fdddfa2.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "30b58d5725fcb34a6fab12282933dd05d6bb69ce806c39567a95cad8fc0c3214", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a898e647801401ed796a16f3eb948f4c106eedfd1262dbe2fc8467de7445d9e6", "generation_seconds_batch": 20.092638136004098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.1020402908325195, "genuineness": 4.6705241203308105, "identity": 0.5337677001953125, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/30b58d5725fcb34a6fab12282933dd05d6bb69ce806c39567a95cad8fc0c3214.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "30b845648802d8dd08d8859afea86124ad25d0e57da5c923b4dd4a87dc266cc0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dbfb4ae09b147939f58b7ec3048407f37bd7b8937b59a938de68c0767ab41ea3", "generation_seconds_batch": 19.92382470902521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 5.879645347595215, "genuineness": 4.457139015197754, "identity": 0.7860366702079773, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/30b845648802d8dd08d8859afea86124ad25d0e57da5c923b4dd4a87dc266cc0.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "311a24e6fea403363bee2de95d5404e15013cf5cf8dcc663d7b6f0bb9940e863", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c5d0155f141c720bbacd7c70270acb70236098d81c7219a3a5fcaac75ffd65f6", "generation_seconds_batch": 22.284973456989974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 5.927301406860352, "genuineness": 4.632867813110352, "identity": 0.641950786113739, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/311a24e6fea403363bee2de95d5404e15013cf5cf8dcc663d7b6f0bb9940e863.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "313b92378853763f15e6f70a30560d75d96f5c7bf0ad4b9786b2ebae37923867", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "133da49fc692aee05634a2a63cb9fa35640f98c24a04826b04b47c6935c9d27c", "generation_seconds_batch": 19.947802798938937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 5.974957466125488, "genuineness": 4.243753433227539, "identity": 0.5588808059692383, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/313b92378853763f15e6f70a30560d75d96f5c7bf0ad4b9786b2ebae37923867.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "317103f5395f4cbfe3f86f7a0657508a07b960d153c090b98973d6beabe57d62", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1534b4319a4f5fac13dcf604a2662265fd5530c54bcee5d61b173855889e71a3", "generation_seconds_batch": 20.899205881985836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.0146708488464355, "genuineness": 4.356721878051758, "identity": 0.6070590019226074, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/317103f5395f4cbfe3f86f7a0657508a07b960d153c090b98973d6beabe57d62.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "31a0bc73f6d9e8fc6cab9316864b39a384d7abdf5afff54fcb9c0cd13c70c6ab", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4abcfa528f2cdefb1a4c14c2dbc6b0c4d08314293618fb5886b04ab59c80d4bc", "generation_seconds_batch": 20.044352402095683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 6.046441555023193, "genuineness": 4.758388519287109, "identity": 0.5029640793800354, "hypothesis": "He encontrado la cajita. Estaba junto a. a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/31a0bc73f6d9e8fc6cab9316864b39a384d7abdf5afff54fcb9c0cd13c70c6ab.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "31ab5ae27dc691e17f308128cd52becd6bb1604e6dcfde241e6a88df01ed99d1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3f8a6a7b4829ffc09828a57f85dc21e542859ad6cfe4d33c93b5002824882a18", "generation_seconds_batch": 16.71838255203329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 5.847874641418457, "genuineness": 4.645420074462891, "identity": 0.5394269824028015, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/31ab5ae27dc691e17f308128cd52becd6bb1604e6dcfde241e6a88df01ed99d1.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "32059cd16de5d7c89c4ea38fb8f9756fdae503a9d500d8ff405d54f03b6e6a9e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5a59ed7721aeb7af46fa9722306e373458b351dc4a6750df753ee1877cbaff47", "generation_seconds_batch": 21.475104095996358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015031516551971436, "target_z": -0.43164062122332164, "ce": 6.23706579208374, "genuineness": 4.6203155517578125, "identity": 0.3939216136932373, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/32059cd16de5d7c89c4ea38fb8f9756fdae503a9d500d8ff405d54f03b6e6a9e.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "32078ad8ee501791ba3e9fb576a9b21117c2f0166b43eef3ead70ddb336ed93a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a86e50f3ca5ce8e707b73bc3e907097e5444349700f198d07bf1a8de1742f7cc", "generation_seconds_batch": 16.19682778499555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 6.070269584655762, "genuineness": 4.65797233581543, "identity": 0.6286530494689941, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/32078ad8ee501791ba3e9fb576a9b21117c2f0166b43eef3ead70ddb336ed93a.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "32214531b937c090b0cf8bdabb7e8e40a7abf2afe9b89aa648ae878c97ab9e9b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ff8ed696304e85ff7065bfeca58242871ffc7459729d60deabaa01b75b745a2", "generation_seconds_batch": 14.801435771980323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 6.181467056274414, "genuineness": 4.143336772918701, "identity": 0.26404833793640137, "hypothesis": "The 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_Shame/32214531b937c090b0cf8bdabb7e8e40a7abf2afe9b89aa648ae878c97ab9e9b.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "32768333f137f5abb0b72014ee0d521700346f25531140cf3b0bc9cb40c69408", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "53127554a9d3ae550266f44e93e5a89c7c45fa808c2d4163ab7f10572372ed9b", "generation_seconds_batch": 22.829683344927616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07810510694980621, "target_z": -0.25390624777842447, "ce": 6.260893821716309, "genuineness": 4.6956281661987305, "identity": 0.3958335518836975, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/32768333f137f5abb0b72014ee0d521700346f25531140cf3b0bc9cb40c69408.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "3363c43c50ecd27390f128f7fe184fdd2fb3b5621d20e041e1fcb3935698d8e0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "927d716ffb0e3c3308e8f3306712710c4d4c360d241bc73068f5caf4748c08d0", "generation_seconds_batch": 19.977619066019543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 5.967014789581299, "genuineness": 4.287685871124268, "identity": 0.4939275085926056, "hypothesis": "The 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_Shame/3363c43c50ecd27390f128f7fe184fdd2fb3b5621d20e041e1fcb3935698d8e0.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "33a3fe99ed93075b091423f103a0fcddcbb3d11969d277a5d29c1d5be8c36b54", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "25b283f6c1865ff1aba741fc081c17389e54fc6bfeb89530dbaf3f04c4b4dfb2", "generation_seconds_batch": 17.454277896904387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.5898406505584717, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/33a3fe99ed93075b091423f103a0fcddcbb3d11969d277a5d29c1d5be8c36b54.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "33c55d73eaf536a7e16dc2244f92213748e1d19ec46853ad8a658a4cf8f1b60e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f84e4fe2262f63d848dadabab88453b372158f980035ee7da3c71bb72bd01988", "generation_seconds_batch": 14.917726065963507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 5.593709468841553, "genuineness": 4.419482707977295, "identity": 0.7078573703765869, "hypothesis": "J'ai trouvé la 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_Shame/33c55d73eaf536a7e16dc2244f92213748e1d19ec46853ad8a658a4cf8f1b60e.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "33eac6b1caf4a26b2cba6585031d028a97e0a8721bcdd0fe16087038205579f8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fff9e248288036e716f5f3f9424f9c0de433395c5b3056e00a3b61fbbb4fdaa7", "generation_seconds_batch": 22.354902556049637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 5.704906940460205, "genuineness": 4.532451152801514, "identity": 0.5671098232269287, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo. Sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/33eac6b1caf4a26b2cba6585031d028a97e0a8721bcdd0fe16087038205579f8.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "9646b0b71fba7d323bdd297ca7da7c346d8da5fcdb8e3a38457801f4d645ee85", "generation_seconds_batch": 14.78002339892555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.1020402908325195, "genuineness": 4.356721878051758, "identity": 0.7929249405860901, "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_Shame/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "heldout-en-2", "language": "en", "sentences": [ "The road turns left behind the bridge.", "Keep going... until you reach the small wooden gate.", "I will meet you on the other side." ], "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-2", "key": "347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414", "bucket": "emo_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "6c09da80cfb9f07e8eea1a308d2c09199966d3f5b4566219c299cc0bbea0fab0", "generation_seconds_batch": 15.189773167017847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.395919322967529, "genuineness": 4.13078498840332, "identity": 0.287422776222229, "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_Shame/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "34881cbd546aea26c98e949783e1c338acb112ca74cfbbda6c16f908ead8759f", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c63f915428538c6948276f59b6fad5ed4aba381a10b79faaee4185a1837a4693", "generation_seconds_batch": 18.180321316001937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04842419922351837, "target_z": -0.31054688321982943, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.5068020820617676, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/34881cbd546aea26c98e949783e1c338acb112ca74cfbbda6c16f908ead8759f.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "349385482b37d59986839d1c3206cc140a3e34946cf0ec06cdf698e246c84d37", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "227530dc4dfbdd92d8efb8614fefd7a868b94c425f98192270eb0534b6e914ff", "generation_seconds_batch": 20.393773288931698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010937601327896118, "target_z": -0.42382812566647265, "ce": 5.855817794799805, "genuineness": 4.758388519287109, "identity": 0.7810947895050049, "hypothesis": "La porte 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_Shame/349385482b37d59986839d1c3206cc140a3e34946cf0ec06cdf698e246c84d37.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "34c49a510e21fb1dcd699d5a7c43ff0eea22dacdd251fbed1c0e075233955a2d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7235913cc6bad363d41b5130cbcdc222d1f5b9e91e12e2ec88941e518144912b", "generation_seconds_batch": 20.48822614690289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053541600704193115, "target_z": -0.3007812495556849, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.7866284847259521, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/34c49a510e21fb1dcd699d5a7c43ff0eea22dacdd251fbed1c0e075233955a2d.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "34fb8afb466606e88a3ccccc53a5af00e126347e109c9c0cc603fbc3223f80cd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "091aaf0dce6fa92fac2fe618aacdbce6baade60710aa3f148e4008df8a73d8ea", "generation_seconds_batch": 24.51609165093396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 5.474569320678711, "genuineness": 4.507347106933594, "identity": 0.5493488311767578, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/34fb8afb466606e88a3ccccc53a5af00e126347e109c9c0cc603fbc3223f80cd.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "357cecc9ef11e1c533e4bce89ab7149c132a9c6fe0a3fca99c18b69fd3f1d3b9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0d8c0d8406d53a25ae4ca252bf43616b439f93755aff371fb2bd4a995711299e", "generation_seconds_batch": 20.950545059051365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 6.268836498260498, "genuineness": 4.281409740447998, "identity": 0.5664453506469727, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/357cecc9ef11e1c533e4bce89ab7149c132a9c6fe0a3fca99c18b69fd3f1d3b9.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "3599d6c4fc03c4bcb23b0beb56ccca27ffe025e999923deb49db0e97b5c78077", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "916ca49c98a060b292356573635f9ff3170fb28dfd2f37d9a95a9ae76aee642f", "generation_seconds_batch": 21.86787215806544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 5.998785495758057, "genuineness": 4.871357440948486, "identity": 0.6651875376701355, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3599d6c4fc03c4bcb23b0beb56ccca27ffe025e999923deb49db0e97b5c78077.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "35bd9e40bde0c6f57e2e93f0a0f531bfabbc395e9e44b39fc025e01a54332aef", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e39e5dda3e2c136a0c7fe6ec13e75042f08df4dd00a35ac00782b7ecd5c0266a", "generation_seconds_batch": 19.98656382993795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.0146708488464355, "genuineness": 4.532451152801514, "identity": 0.5979396104812622, "hypothesis": "La porte 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_Shame/35bd9e40bde0c6f57e2e93f0a0f531bfabbc395e9e44b39fc025e01a54332aef.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "35c93211888e2ab28c3e6a06e6012f79ab89cf084a1052cc3da332aac4c884f0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c12e50ca96d18136405d1faec705a8441adf27f6cedefc1b5f91073d815b349d", "generation_seconds_batch": 20.560154892038554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.109982967376709, "genuineness": 4.6705241203308105, "identity": 0.815351128578186, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/35c93211888e2ab28c3e6a06e6012f79ab89cf084a1052cc3da332aac4c884f0.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "362fdc0d38af32cbb749831f44301ab7e835f9438ecd6cfd114e8af61863a3ce", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bda6c28ac6f99d711dcd0a58a24a3bcdbbae2a3fa33f2fce6c9a033c0a8e92ae", "generation_seconds_batch": 20.794989787973464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 5.998785495758057, "genuineness": 4.494794845581055, "identity": 0.4613943099975586, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/362fdc0d38af32cbb749831f44301ab7e835f9438ecd6cfd114e8af61863a3ce.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "364ca4255edb28bf9114ee192a79f0f739a4a93fc0cb97f620bf2298352ee59b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "838d38a69b466a86c5110838c3e186d65711a3b839a17bb3e6d414211bd1b65c", "generation_seconds_batch": 19.980031076003797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 6.268836498260498, "genuineness": 4.607763767242432, "identity": 0.3844062387943268, "hypothesis": "The 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_Shame/364ca4255edb28bf9114ee192a79f0f739a4a93fc0cb97f620bf2298352ee59b.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "3756a8aa5026879af4d4366a8444bd4c5a94e42d99a95677ed6328a87a7ca979", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8575e71b7453d0a24f7ad40ee07b039f620ef6c6c4c7e1ccfff85789b5bf187f", "generation_seconds_batch": 20.952861405094154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 6.1894097328186035, "genuineness": 4.645420074462891, "identity": 0.7328006029129028, "hypothesis": "J'ai trouvé la 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_Shame/3756a8aa5026879af4d4366a8444bd4c5a94e42d99a95677ed6328a87a7ca979.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "379cd10e57def40859e3c108bd85beef64c6e128afc3f2756cab597d6600237c", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "56a5047f3e481ccd1a0e9ae20cf4b22ab0b285be4d1fddbab6027d6c4b02b82e", "generation_seconds_batch": 16.03534888289869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.8199385404586792, "hypothesis": "J'ai trouvé la 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_Shame/379cd10e57def40859e3c108bd85beef64c6e128afc3f2756cab597d6600237c.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "38099cf8bc20c099089a77fdb6e76ea3291579227cbcf97633fd1ec87f7f5a91", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "87ba13ff915496829be2c8ffaf674d18de771888ad6c1576a56e1a6950682a83", "generation_seconds_batch": 24.73696795105934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.6388373374938965, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/38099cf8bc20c099089a77fdb6e76ea3291579227cbcf97633fd1ec87f7f5a91.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "380bea4acb6e24d1e4f15722747dfac228cca0b0ef177c79fd89d3de5adce638", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "915f57025d82071857058349f1a84e3a67520b426caadaf4085c1e70bad90ddd", "generation_seconds_batch": 22.187535247998312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 5.577824115753174, "genuineness": 4.21237325668335, "identity": 0.5744055509567261, "hypothesis": "J'ai trouvé la 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_Shame/380bea4acb6e24d1e4f15722747dfac228cca0b0ef177c79fd89d3de5adce638.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "3857de2625f1b3b4b6e13f8cf3291ce1e4ad7e88ef7847cf4681a4fe4d2fd910", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1d98befbf3bbaf6d75f81a98c3c98f84716f541f8e7b08a9da9a1be911b2a9e8", "generation_seconds_batch": 14.62049587292131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0017262846231460571, "target_z": -0.40624999644547916, "ce": 6.165581703186035, "genuineness": 4.532451152801514, "identity": 0.2578129768371582, "hypothesis": "The 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_Shame/3857de2625f1b3b4b6e13f8cf3291ce1e4ad7e88ef7847cf4681a4fe4d2fd910.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "38835270828548bfd47f24a0e30c7a86cd338bb498753a1f1b8f9d91e8dee89e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2e103f6322c263aaf77f8860dd7521b8f6669562d11452583dc93f2735b5335d", "generation_seconds_batch": 20.53731897904072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.796247482299805, "genuineness": 4.406930446624756, "identity": 0.7614706754684448, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/38835270828548bfd47f24a0e30c7a86cd338bb498753a1f1b8f9d91e8dee89e.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "3898fabdd54289d87262243bba973c28276fdd6d6826d9cee987d5b99cfb8317", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ed0bca9d1b4da34134da15ad050aee39ad62e3c5040ad95d28ae7e02808fbb94", "generation_seconds_batch": 20.544169612927362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 6.149696350097656, "genuineness": 4.7458367347717285, "identity": 0.5058343410491943, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3898fabdd54289d87262243bba973c28276fdd6d6826d9cee987d5b99cfb8317.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "3984ef6cc113dd6cbdbbc674f7b7328c61d56e0c395ce396d7168ea792c0a501", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "93308b27e82294202ec08eaeb804c5b81cba5de5f7e500dca93689d3e5817469", "generation_seconds_batch": 20.251263079000637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 5.831989288330078, "genuineness": 4.118232727050781, "identity": 0.5026833415031433, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3984ef6cc113dd6cbdbbc674f7b7328c61d56e0c395ce396d7168ea792c0a501.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "39c8351d863a4ac232245e7bc62a8ea35e5d4179b18e585aff51776519e377bf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1486ebe2b9d1672e8bbb61787d95748da8ac28b42b6555099004d55d87f4be5f", "generation_seconds_batch": 20.502163465018384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.157639026641846, "genuineness": 4.162164688110352, "identity": 0.224190354347229, "hypothesis": "The 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_Shame/39c8351d863a4ac232245e7bc62a8ea35e5d4179b18e585aff51776519e377bf.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "39c936ce100684450bd3154ab65f8d8425bd200222da38afb091c57f1841ca30", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e9dcc2777eb2c5c07a7c88ae38adf67e87f6f196a5a7bebde12329fecedcc413", "generation_seconds_batch": 23.71437728893943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.4230082333087921, "hypothesis": "The 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_Shame/39c936ce100684450bd3154ab65f8d8425bd200222da38afb091c57f1841ca30.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "3a438124d7f8fbf23fc3e1f6b708cf91b273fa4e6328a1968bd87f8d1499f677", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d74b544f3f0819badfc1aa2914e2e64d3f531d801bb9de6e8e741480ae6def5c", "generation_seconds_batch": 19.864949120092206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.38003396987915, "genuineness": 4.406930446624756, "identity": 0.5078927278518677, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3a438124d7f8fbf23fc3e1f6b708cf91b273fa4e6328a1968bd87f8d1499f677.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "3ab5d9f418965f267c1793623e58e61ce7db6065f899336bd12b567475cdef55", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a904eaedd73e5ffd05b2b014d0280049dd3cfbe69018da007e323e14434fd159", "generation_seconds_batch": 14.83345873793587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.054384231567383, "genuineness": 4.557555198669434, "identity": 0.6313225626945496, "hypothesis": "La puerta sigue abierta y dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3ab5d9f418965f267c1793623e58e61ce7db6065f899336bd12b567475cdef55.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": "3af06cddfd67b25a70b5bfa3d99cd0edf04d1b69b70aa82a75af91f37096548f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "63eb51579032fe7fb03ffc08f2112652afb0cde0aa16b422a01cf7125b4af7d1", "generation_seconds_batch": 17.301141466014087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 6.268836498260498, "genuineness": 4.356721878051758, "identity": 0.541332483291626, "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_Shame/3af06cddfd67b25a70b5bfa3d99cd0edf04d1b69b70aa82a75af91f37096548f.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "3b3a562f0b474dbe464346188c3a0f61647ebadd99dd4897b98f320812fff83d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6b3250069d08c589e6419bf46d3194716f1c1b1b7d2dcb09c25eb13592cd91b4", "generation_seconds_batch": 16.21274096297566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 6.141753673553467, "genuineness": 4.632867813110352, "identity": 0.7982831001281738, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3b3a562f0b474dbe464346188c3a0f61647ebadd99dd4897b98f320812fff83d.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "3bd73583f3840bc40ec4e268e2a18748f38857be32c958f81ac80046eca516b9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cd32948b1a45771d5ea0398da2f47183b24493953e2225d079a1011a04ac13d3", "generation_seconds_batch": 15.916080081020482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 5.748591423034668, "genuineness": 4.356721878051758, "identity": 0.17118477821350098, "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_Shame/3bd73583f3840bc40ec4e268e2a18748f38857be32c958f81ac80046eca516b9.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": "3c12d4803d3885c7a2cda33b42d97b352dce29f7ecee0aa3a8de466a156c8d83", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e370beefcb99e8fb8855979a6196cffa0289b105b8394a1624d6b8dbbcc8e680", "generation_seconds_batch": 20.304031734005548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 5.704906940460205, "genuineness": 4.218649387359619, "identity": 0.41762739419937134, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las ze 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_Shame/3c12d4803d3885c7a2cda33b42d97b352dce29f7ecee0aa3a8de466a156c8d83.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "3c2567fb7af69e812e8ea63029526c3b885c85ae07b13130314cb8ecda8beaef", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6db1f9143c1f4b531eef7b27ef8e03243aa2c28ddc303f12a6fd1b331fc94f0f", "generation_seconds_batch": 21.526654524030164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.109982967376709, "genuineness": 4.406930446624756, "identity": 0.6496686339378357, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3c2567fb7af69e812e8ea63029526c3b885c85ae07b13130314cb8ecda8beaef.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "3e4241bf2d3d63780e2b227aa146aa5cba86101fb37221359a6b1eb3a44acbfd", "generation_seconds_batch": 16.81026073708199, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.213237762451172, "genuineness": 4.394378662109375, "identity": 0.3890497088432312, "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_Shame/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "3d4c6e5917e17909e1be77fb2a9951278755f4781266bc16dd77d6ab1f8fe961", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "417c5199b39ba394ff51009f0b344841dd1bf39e658edb26ed7d14a54843b31a", "generation_seconds_batch": 20.232087623910047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 5.855817794799805, "genuineness": 4.6956281661987305, "identity": 0.6601605415344238, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3d4c6e5917e17909e1be77fb2a9951278755f4781266bc16dd77d6ab1f8fe961.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "3d5c886bffb407eacf762d435d6a08934d30fe15724811785480624101acb109", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6fb4d3ff410244d17933994973a74d978f331081197bf464279d759e106ef5e9", "generation_seconds_batch": 20.90941343002487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.149696350097656, "genuineness": 4.532451152801514, "identity": 0.7302694320678711, "hypothesis": "Ik heb het een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3d5c886bffb407eacf762d435d6a08934d30fe15724811785480624101acb109.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "3d6be3525c98a52fd8ebb3eea32766dd6742461927b185b192aad45b1ba6a2b0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "77c1c6a4a71206ddc7778ab235a2d56aa8157189a60f039e4b174594e922f413", "generation_seconds_batch": 22.507037086994387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 6.221180438995361, "genuineness": 4.300237655639648, "identity": 0.3967636227607727, "hypothesis": "The 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_Shame/3d6be3525c98a52fd8ebb3eea32766dd6742461927b185b192aad45b1ba6a2b0.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": "3d7d32ac76ae8359a58ad303955252a674ee3185c01bb6e17c7e7f03de0a5953", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "85990803905153590a164bc397f0e22b29c896d8ead0f4d98a2ed158dd9521f4", "generation_seconds_batch": 14.492139465990476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 5.6334228515625, "genuineness": 4.030367851257324, "identity": 0.5326331257820129, "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_Shame/3d7d32ac76ae8359a58ad303955252a674ee3185c01bb6e17c7e7f03de0a5953.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "3dd63216565298175fe1dc40f4b6d69782afcc97204624586f791a8ecbdda5e4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "12a7ab6f8d6aade6ba38642c28a22eb3c4b06f0fa89c3210d87a82cd891427b2", "generation_seconds_batch": 20.565472154063173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 5.839932441711426, "genuineness": 4.030367851257324, "identity": 0.5649756193161011, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3dd63216565298175fe1dc40f4b6d69782afcc97204624586f791a8ecbdda5e4.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "3eeefb40613667dd532dd23c9f9f8bf9e12da9bb5da4b96c6079203800e1304a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "902f400d9abbc5d504cccd8d2524a4b34b5da1f4292599fca5feff96639532f9", "generation_seconds_batch": 20.802230881992728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.229123115539551, "genuineness": 4.293961524963379, "identity": 0.5170748233795166, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/3eeefb40613667dd532dd23c9f9f8bf9e12da9bb5da4b96c6079203800e1304a.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "403c1a001db03ace0ba078eb75b8b5c84393aeb204a9f16c8df3452e9c41447c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8d692afa0a9fb527de7cb0d1bd75c85fb13a4e1ee621144f92c4454d2cf61aa0", "generation_seconds_batch": 20.3818281639833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.340320587158203, "genuineness": 4.808597087860107, "identity": 0.8659431338310242, "hypothesis": "J'ai trouvé la 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_Shame/403c1a001db03ace0ba078eb75b8b5c84393aeb204a9f16c8df3452e9c41447c.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": "40eafb3e8f8cb875ea1a839d20f1295adb844a2ddb51df2b8e49207a18c2556f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "5250708357c9f493d7247dcb2f6db4a26fec6bc7902b7fd428a5a4aea00d193c", "generation_seconds_batch": 14.57366540597286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 5.855817794799805, "genuineness": 4.394378662109375, "identity": 0.21040774881839752, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed? En controleer de laatste twee cijfers. Bel me, wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/40eafb3e8f8cb875ea1a839d20f1295adb844a2ddb51df2b8e49207a18c2556f.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "41a84175bcdbb4222d56f94db727bf45d53dd26f38e34e9d5af2967bd010a2a9", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3ef1d7c7042a4e433c0b33cb4398710981ecf50eacec5e09e00e911f806d14f7", "generation_seconds_batch": 16.13053075503558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 6.435632705688477, "genuineness": 4.519899368286133, "identity": 0.4723268747329712, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/41a84175bcdbb4222d56f94db727bf45d53dd26f38e34e9d5af2967bd010a2a9.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "41da24bf5a3cf8c4bc3da622e79f31d961d946d81ce5574772ef46304da8a1e7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c24a299214164eca048071d87e3645a0aafd29e2e83fe2692c010fcbc47d7ac4", "generation_seconds_batch": 20.09122965403367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 5.8875885009765625, "genuineness": 4.68307638168335, "identity": 0.5697526335716248, "hypothesis": "La porte 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_Shame/41da24bf5a3cf8c4bc3da622e79f31d961d946d81ce5574772ef46304da8a1e7.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "42215030c0593cbfba8939298d2c13cb9380900a1d85db1975cbce1a3fb499c6", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d70d51737d54f8cf48cdd7c79b171966643d5ef2af56298a3c286db73656aaef", "generation_seconds_batch": 17.317455382901244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 5.974957466125488, "genuineness": 4.005263805389404, "identity": 0.34095287322998047, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/42215030c0593cbfba8939298d2c13cb9380900a1d85db1975cbce1a3fb499c6.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "42242ff6d511a25f613e43e9a02c5e9bfec7555fa6dd22fe6366267cbe468e33", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b29eb3bcf1c0bafc9288eae23ca5e4f5380c69474d0f537b9c8eb642bab17367", "generation_seconds_batch": 18.068825416034088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 5.816103935241699, "genuineness": 4.758388519287109, "identity": 0.7911268472671509, "hypothesis": "J'ai trouvé la 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_Shame/42242ff6d511a25f613e43e9a02c5e9bfec7555fa6dd22fe6366267cbe468e33.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "425e1ed3a4d3747662e60dc7b27739b66c5f0fd2838bb07e87c4f1a1b85a1a3a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "442b27c64fda94ef707c4238290d6dc8c078de0419ed3b2a6138917787ccfcd1", "generation_seconds_batch": 21.436078867060132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 5.911416053771973, "genuineness": 4.645420074462891, "identity": 0.7074935436248779, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/425e1ed3a4d3747662e60dc7b27739b66c5f0fd2838bb07e87c4f1a1b85a1a3a.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "4263fb6ae48e4b58bf2186ca0dc5aa0da98d6675e757396159a92c1ddff07e83", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "73a3267cd8410905caf760831da7af51fc9d923a821ef382f1ec39858d2f49e4", "generation_seconds_batch": 20.90892271406483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 6.022613525390625, "genuineness": 4.632867813110352, "identity": 0.7552069425582886, "hypothesis": "La porte 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_Shame/4263fb6ae48e4b58bf2186ca0dc5aa0da98d6675e757396159a92c1ddff07e83.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "42df17fbdc6bbc218a71d4e017f7a944bbbf89b51b0b84973fa7ef08ef2cc4bf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5510e0e073cfe6c8ad1803214243f0621487d787586033546c963afc5eb1425d", "generation_seconds_batch": 17.00375408900436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 6.1894097328186035, "genuineness": 4.494794845581055, "identity": 0.5638295412063599, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/42df17fbdc6bbc218a71d4e017f7a944bbbf89b51b0b84973fa7ef08ef2cc4bf.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "4319c90e982cd0847770be3568a9f2591bf82663c1ac925827410cf170f59d55", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "666ef1aa5ddb57f3a3a869cacaca2bd8a98c7e52b5dedf568f642a37f7d91a4f", "generation_seconds_batch": 20.206565120024607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 6.427689552307129, "genuineness": 4.482243061065674, "identity": 0.5820386409759521, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4319c90e982cd0847770be3568a9f2591bf82663c1ac925827410cf170f59d55.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "d8fbc21ca0e886280a5bad14da1fb2ed5c706707f0291f6246b92ca6540ffc83", "generation_seconds_batch": 14.78002339892555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.205295085906982, "genuineness": 4.413206577301025, "identity": 0.7051669359207153, "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_Shame/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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "09ab6e1035cbe95f2a8dca62894ad742c28b4fbf854795cee67d166f2627e999", "generation_seconds_batch": 16.49546048103366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.205295085906982, "genuineness": 4.68307638168335, "identity": 0.47919169068336487, "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_Shame/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "43ec4037692edb7364ca4db1157797f57b2544cda12adfcb67deba587c8f0b14", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "494b86652b7ecf1398f8f56100dc1a826417ca96ef8f68b79b0e3b814816ec18", "generation_seconds_batch": 14.94140085496474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03614245355129242, "target_z": -0.3339843698903763, "ce": 6.0305562019348145, "genuineness": 4.846253395080566, "identity": 0.7589552402496338, "hypothesis": "J'ai trouvé la petite boîte elle était près de près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/43ec4037692edb7364ca4db1157797f57b2544cda12adfcb67deba587c8f0b14.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "44466027a58815b953423241f3c2772e88676bb0d7d8aa174ef956ba621995dd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4cbb66d500001c5d776dcb68e07e9d75a869fb0b6e1fb4f9129971c93ad8329f", "generation_seconds_batch": 16.179308263002895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.229123115539551, "genuineness": 4.268857479095459, "identity": 0.7144729495048523, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/44466027a58815b953423241f3c2772e88676bb0d7d8aa174ef956ba621995dd.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "457bbf5b6349f211aa01824d9a737cde50fba4488430783fd8e904a7139769ee", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "05c567e5a9642b06feca378f5ed139509e1e22bf97923b3d33e9911f16c65fb0", "generation_seconds_batch": 20.125160275027156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.855817794799805, "genuineness": 4.607763767242432, "identity": 0.6141369938850403, "hypothesis": "J'ai trouvé la 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_Shame/457bbf5b6349f211aa01824d9a737cde50fba4488430783fd8e904a7139769ee.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "45c1ec8961bf1cbad3417b4191c75d59bf4b7956c6e9a991254b251460085b4c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "83ea3e4bdd4443968f02b05df8e3df51739f64743771955d980c5b576eada9c5", "generation_seconds_batch": 20.534617764991708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.23706579208374, "genuineness": 4.607763767242432, "identity": 0.39101654291152954, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/45c1ec8961bf1cbad3417b4191c75d59bf4b7956c6e9a991254b251460085b4c.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "45c88d5f969287860fc709e4099295984ec548a916c078f913bf7331cdbea857", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1ac4f809efc7d68a91a56838467ea37425a21fb1caf20b4ea8b93c7f9d80dac4", "generation_seconds_batch": 16.297621017089114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05865900218486786, "target_z": -0.29101561589154035, "ce": 6.252951145172119, "genuineness": 4.65797233581543, "identity": 0.7770410180091858, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/45c88d5f969287860fc709e4099295984ec548a916c078f913bf7331cdbea857.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "88c70cf5e94b87eaf03d35b044af91111b08d9f4844a3376c7fc538adc827407", "generation_seconds_batch": 16.271461609983817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03614245355129242, "target_z": -0.3339843698903763, "ce": 6.332377910614014, "genuineness": 4.143336772918701, "identity": 0.6712353229522705, "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_Shame/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "46b44742e8a7cf834cfd294eb578b336cda6a7474993162adc027fc1b9fa6499", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c4780a0ad4cdacaa7f31d05a0e71d09594714dc0badd8be494acb54618b90e6e", "generation_seconds_batch": 20.48269936197903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 6.268836498260498, "genuineness": 4.300237655639648, "identity": 0.4474632740020752, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/46b44742e8a7cf834cfd294eb578b336cda6a7474993162adc027fc1b9fa6499.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "46ec68ee184c757ac377f96314cd7c0751d81dbd7b934c489eca3208bfc7deb8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f8436da4863eb719506d5efb2d9f87f305a2a2d5ee6656f420256e96484f766a", "generation_seconds_batch": 20.494558933074586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 5.855817794799805, "genuineness": 4.557555198669434, "identity": 0.660575807094574, "hypothesis": "La porte 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_Shame/46ec68ee184c757ac377f96314cd7c0751d81dbd7b934c489eca3208bfc7deb8.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "4729cb58c351334bbfa81c15ac2117253a520107c389f578df746f2b9e9daddb", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9bad4ef526dbd3709bcd0d7bb94d58c4e3403ffbfda5473b58d3ed9b77e36c9a", "generation_seconds_batch": 22.284973456989974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.0305562019348145, "genuineness": 4.6705241203308105, "identity": 0.6240203976631165, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4729cb58c351334bbfa81c15ac2117253a520107c389f578df746f2b9e9daddb.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": "478217b672bd130172591b735fd7e90ee306062f56197be86afa7c9e6d4188fd", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "d6dc22b339ae8b15dae826fd1b03a5f0ce83eaffd91329d9e082aa94d6f4da7e", "generation_seconds_batch": 16.636159666930325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 5.935244083404541, "genuineness": 4.344170093536377, "identity": 0.520683765411377, "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_Shame/478217b672bd130172591b735fd7e90ee306062f56197be86afa7c9e6d4188fd.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "4786b5d14302d9d5542618d63d220954f2cd0affd7b5f47c0d23211f3020d2f0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cfd06a6e2066812e36b0969a116214d8e4db9564cb209417252c6f92673ec3d6", "generation_seconds_batch": 14.926657047937624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02014891803264618, "target_z": -0.44140625488746615, "ce": 6.062326908111572, "genuineness": 4.7458367347717285, "identity": 0.7121641635894775, "hypothesis": "He encontrado la. la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4786b5d14302d9d5542618d63d220954f2cd0affd7b5f47c0d23211f3020d2f0.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "47c7a497e9d3d41b54b3f76628249e26539a8763636b268d1bf5de87b066f3bf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "19fd7f1311ac4ec612ccbd68a2fea67605f5893f1766adc4f314171fa3935b02", "generation_seconds_batch": 20.561961513012648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.736922025680542, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/47c7a497e9d3d41b54b3f76628249e26539a8763636b268d1bf5de87b066f3bf.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "f52e0831a4fe968603463b620fa952e2d250cf302aab71ea601d88a7b9dbd56c", "generation_seconds_batch": 14.979881579056382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.1894097328186035, "genuineness": 4.6203155517578125, "identity": 0.7174285650253296, "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_Shame/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "47f8b55c5bec44719e89b7075dd4395e0ece2bb4819691b2df06d03e6ff29769", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "abef1eadbe03bdd977641665ceed6abf4f52f60d6ade0468b90b2cb9f18e4072", "generation_seconds_batch": 14.840334779000841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 5.80021858215332, "genuineness": 4.570107460021973, "identity": 0.7121700644493103, "hypothesis": "J'ai trouvé la 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_Shame/47f8b55c5bec44719e89b7075dd4395e0ece2bb4819691b2df06d03e6ff29769.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "4819248b61c7531d6368f11aecf67c132cf0b787545b480aa072780e0ae6b43b", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d5c5b2f7c8ce2becb0abee563f999a73012bf34301e879d885d19330ff95e0cb", "generation_seconds_batch": 18.180321316001937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.197352409362793, "genuineness": 4.519899368286133, "identity": 0.7275967001914978, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4819248b61c7531d6368f11aecf67c132cf0b787545b480aa072780e0ae6b43b.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "4897d67092f393fb2c5b44cac5ed7eef6d5f22741d2d4b350e1f73de173cdee3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6bda2838781ea52df60348cbc094774dba6aa56d28a3b349307b0b060e635174", "generation_seconds_batch": 19.972217981005087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 5.728734970092773, "genuineness": 4.632867813110352, "identity": 0.6486992239952087, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4897d67092f393fb2c5b44cac5ed7eef6d5f22741d2d4b350e1f73de173cdee3.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "48a7db81241d33c46afa1e09ee8dd8f07795cb35a10c47ab3e789ab8ec8ce84e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "df46fec39acd0c84f075bedaab7211f443f44126c4b0e8b9b4db5ff1c3fb7fab", "generation_seconds_batch": 19.9634273420088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 6.046441555023193, "genuineness": 4.507347106933594, "identity": 0.7090007066726685, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/48a7db81241d33c46afa1e09ee8dd8f07795cb35a10c47ab3e789ab8ec8ce84e.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "48efc8328dc34c1efe1dbecd7074365a7371fb48e37d8aa30f057c86c998e7c8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f26d8c4ca5c97ef00aca164efedc634d0e9cc916488abfa834c2c2f125c74247", "generation_seconds_batch": 20.85130067402497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.24500846862793, "genuineness": 4.375550270080566, "identity": 0.43062007427215576, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/48efc8328dc34c1efe1dbecd7074365a7371fb48e37d8aa30f057c86c998e7c8.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "491e7102d47c8aa3601017756626f28b8195d8d2f17b78d11a41b8bb9804df6d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "296dd82bc3549cb498575ffeffb1bae3c64e2795b76994ec1730f771a81cc326", "generation_seconds_batch": 20.546010551974177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.38003396987915, "genuineness": 4.432034492492676, "identity": 0.4209054708480835, "hypothesis": "The 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_Shame/491e7102d47c8aa3601017756626f28b8195d8d2f17b78d11a41b8bb9804df6d.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": "493056ae5ec436d85e5116ff30dada26310b6c2962747d01491071c9301207bf", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "a64ca4a762c525bde2f2b3333ea47bbb9fd6fed71414b232ec3b911711f909a2", "generation_seconds_batch": 14.975685399025679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 6.292664527893066, "genuineness": 4.099404335021973, "identity": 0.5831207633018494, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. How 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_Shame/493056ae5ec436d85e5116ff30dada26310b6c2962747d01491071c9301207bf.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9270b22afe0f4455472ec527871bd2dd2c547bd8914cc36b6558c777e53d4bd", "generation_seconds_batch": 14.85626734001562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.7296962141990662, "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_Shame/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "4a0421c455f871597fc3b8c8cb4fe82bf88de42d7538e639e6116f6cd2b0476f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "affb367a53504f6647c1d7af685c6aed3db54452a362dad0f76eec29b0aa5c4b", "generation_seconds_batch": 21.408640939975157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.546053409576416, "genuineness": 4.507347106933594, "identity": 0.7081379890441895, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4a0421c455f871597fc3b8c8cb4fe82bf88de42d7538e639e6116f6cd2b0476f.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "4ab3a29b61b1aa644b6ab8172cc3192227f66cf58091a2e4628c636d0e05ea24", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ceaffadc6b92988ab5f64695e3bd9be8ee2321b7d340ba41892411525860a09d", "generation_seconds_batch": 20.07251875801012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.252951145172119, "genuineness": 4.758388519287109, "identity": 0.6157569885253906, "hypothesis": "La porte 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_Shame/4ab3a29b61b1aa644b6ab8172cc3192227f66cf58091a2e4628c636d0e05ea24.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "4ab76d00336bd04ab8b8d3f4e8e4c966090f263ebcc410dec44da0d25e4122ad", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f6a870e7cf8f5dde59b42c4f7fa462788222cba38e10ff09de07d458cc645710", "generation_seconds_batch": 14.687219031038694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.395919322967529, "genuineness": 4.344170093536377, "identity": 0.3858465552330017, "hypothesis": "The 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_Shame/4ab76d00336bd04ab8b8d3f4e8e4c966090f263ebcc410dec44da0d25e4122ad.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "4b62ce22db4c695e71e3eec02a9dd494e388b109c140954af010f54db2d53b53", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "06b9a150c00c87fb850d97d26aea98598122e74f4937c1e752fde23cecfd4e19", "generation_seconds_batch": 14.721013586968184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05494721233844757, "target_z": -0.5078124955568489, "ce": 5.252174377441406, "genuineness": 4.432034492492676, "identity": 0.6223905086517334, "hypothesis": "La porte 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_Shame/4b62ce22db4c695e71e3eec02a9dd494e388b109c140954af010f54db2d53b53.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "4c9a280951e114ec4cdff189fd69bf6a45a5cd15f27abaacef83e0533ffd96de", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2c08cb75abddbcfacb072ca602ca8c7f8f7d2ba600857127f487d478511e0d2c", "generation_seconds_batch": 16.03534888289869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.855817794799805, "genuineness": 4.808597087860107, "identity": 0.7409317493438721, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4c9a280951e114ec4cdff189fd69bf6a45a5cd15f27abaacef83e0533ffd96de.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": "4d0b721a27798ee47aff60a4818bc4e29a130ccadaf5593916ee7a6a38e6387c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a401f69b22752a3f26a717571f54cbb699e3f7879441fb9546a4adee7d4a04e5", "generation_seconds_batch": 14.604511679965071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06787031888961792, "target_z": -0.2734374866705469, "ce": 5.95112943649292, "genuineness": 4.457139015197754, "identity": 0.7223908305168152, "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_Shame/4d0b721a27798ee47aff60a4818bc4e29a130ccadaf5593916ee7a6a38e6387c.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "4d5c2d04eecf215e67d0748b41ec8655aabd4b93405fa074b32e47636fc92fdf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "20836bde1de2df3c3097e7e58f81b8e34fcf7167ef52215e8571360eb786a543", "generation_seconds_batch": 20.556077703018673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 5.959072113037109, "genuineness": 4.570107460021973, "identity": 0.5895887613296509, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4d5c2d04eecf215e67d0748b41ec8655aabd4b93405fa074b32e47636fc92fdf.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "4d60b0ef7f3ecb60ac9f0a18f8c0f5f12dca48743aba052b397aaae2919c8d55", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "814362c9d8b7fdcdcfed900df3a76152f8ef105a8c957256f9483fb93cdc76fb", "generation_seconds_batch": 16.62110972602386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 6.09409761428833, "genuineness": 4.7081804275512695, "identity": 0.788011908531189, "hypothesis": "J'ai trouvé la 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_Shame/4d60b0ef7f3ecb60ac9f0a18f8c0f5f12dca48743aba052b397aaae2919c8d55.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "4e0a9e753493c9b3e4cb4da782241e1dc7831b814bc75264c3ecef3c1b635a7d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "eb827d290c92d895afb93864e932208457f531ee74531280f659d68924e0bd08", "generation_seconds_batch": 20.899205881985836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 6.1020402908325195, "genuineness": 4.444586753845215, "identity": 0.5330966711044312, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4e0a9e753493c9b3e4cb4da782241e1dc7831b814bc75264c3ecef3c1b635a7d.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "4e14a507806f1fff8c59a0215244919e6caba9947fd4908d804d3eb6a7549bdd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8e99f2e6a29e4817cac14548e88e48b2f94b8e1bdf9a8fc3342fe774c4decdc6", "generation_seconds_batch": 20.237323093926534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06275291740894318, "target_z": -0.2832031203346914, "ce": 5.903473377227783, "genuineness": 4.7458367347717285, "identity": 0.7744889855384827, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4e14a507806f1fff8c59a0215244919e6caba9947fd4908d804d3eb6a7549bdd.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "4e45a03f5a6911b1516bf205dc193cdc22cf25f22b75ffa38c75a061fd9a7697", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "311fc676bd73e09e71d6d298739587b2b98ea83090bf17a9c521b46bcdd8560a", "generation_seconds_batch": 20.794989787973464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 5.855817794799805, "genuineness": 4.6956281661987305, "identity": 0.7300061583518982, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4e45a03f5a6911b1516bf205dc193cdc22cf25f22b75ffa38c75a061fd9a7697.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "4e4f685aaa897219de7fe636d4df11a18242450884fa37798d2716486d228294", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8c45a8f1c4f3d53479e9a02c12ed7851fea9cb0f51e398a1660653b234d1d171", "generation_seconds_batch": 23.550676433951594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 5.982900142669678, "genuineness": 4.457139015197754, "identity": 0.16207100450992584, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4e4f685aaa897219de7fe636d4df11a18242450884fa37798d2716486d228294.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": "4e702de1fd29c092b96a11c2d94dc45eed90c27a0df83995bb3557d4541bc09f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "f0c89d9def2fa4020c1926cb598a913c75a78ea51d18e3b8c5facc7d05c54b6a", "generation_seconds_batch": 17.268023142940365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.959072113037109, "genuineness": 4.6705241203308105, "identity": 0.6750694513320923, "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_Shame/4e702de1fd29c092b96a11c2d94dc45eed90c27a0df83995bb3557d4541bc09f.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "4ee3e0924f87c83aef2c236d47fb6113260186e06cdc5a0165ff9eb710446b22", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "39a8e435148c90d53f216128d06f7c0d5a6eca605b2615660856b910486785db", "generation_seconds_batch": 20.33373983099591, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 5.784333229064941, "genuineness": 4.68307638168335, "identity": 0.770162045955658, "hypothesis": "La porte 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_Shame/4ee3e0924f87c83aef2c236d47fb6113260186e06cdc5a0165ff9eb710446b22.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "4f4534d1ce5bed3a5554882a841016a448927f6c474fd6103d8f93590eee0169", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "95000edd3048034a6e01f22e492ad8b4b3f45b58b02e0c764182bcad209aa63d", "generation_seconds_batch": 20.11715311498847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0027497708797454834, "target_z": -0.40820313455277474, "ce": 6.2767791748046875, "genuineness": 4.595211505889893, "identity": 0.4649508595466614, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4f4534d1ce5bed3a5554882a841016a448927f6c474fd6103d8f93590eee0169.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "4f8f6a2175ad727656f677cbabc8e1e58a8fd9fe36f63cb9bccda1a29b2ab512", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c44affe2f46c57447571aa4aba0cd7cff9063ef7e22f068176b82001f08d445", "generation_seconds_batch": 20.81881781190168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 6.046441555023193, "genuineness": 4.8588056564331055, "identity": 0.5389224290847778, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4f8f6a2175ad727656f677cbabc8e1e58a8fd9fe36f63cb9bccda1a29b2ab512.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": "4fcd631a72e0429452e204297ed2a213e0d5e5e8236de9c4b57aa4729e39a081", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5d65c6575f147891fb7cf3f081916085ff5c790db51c031b9faafc725654f660", "generation_seconds_batch": 22.91679574002046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.284721851348877, "genuineness": 4.444586753845215, "identity": 0.5439409017562866, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4fcd631a72e0429452e204297ed2a213e0d5e5e8236de9c4b57aa4729e39a081.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "4ffc736302aa2b534dcc46de0cb3f63591e6b77157f7b2a6be8c65d9623654b0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e8a087be92fd7696a7036c78c239946423d9decf69c3ebfc46f57cf247e59038", "generation_seconds_batch": 14.723172578029335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 6.0305562019348145, "genuineness": 4.2374773025512695, "identity": 0.5097732543945312, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/4ffc736302aa2b534dcc46de0cb3f63591e6b77157f7b2a6be8c65d9623654b0.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "5006881c51971034f5d9314011ad7674ffb92698f928f00cb6245df18682d253", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "004c8b722daa119699c25064bcf0dec83581070d8bbc48de5a25f461225b04bb", "generation_seconds_batch": 19.99357511207927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08526946604251862, "target_z": -0.24023436633585546, "ce": 5.7247633934021, "genuineness": 4.570107460021973, "identity": 0.5718153119087219, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5006881c51971034f5d9314011ad7674ffb92698f928f00cb6245df18682d253.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "500d20c63c6938b532536e7346ca403891b878a59b429639c3683d7fb63d5e03", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b4b37589bc9b360c04be92c5860df2d34956ed0fb09c4f516ab4a6c54476e439", "generation_seconds_batch": 16.71838255203329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.0305562019348145, "genuineness": 4.7458367347717285, "identity": 0.6386163234710693, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/500d20c63c6938b532536e7346ca403891b878a59b429639c3683d7fb63d5e03.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": "5013982485154d9d35b35d6d8ec06dd66083dd74a0e2b6766942b8418051b704", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f69173ce841c6eda51589b5d9d09061341827870d924c2ee2bacaa21aa08ed92", "generation_seconds_batch": 14.764835605048575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.375286102294922, "genuineness": 4.068024158477783, "identity": 0.7342849373817444, "hypothesis": "Die Straße führt hinter der Brücke nach links. Ich geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5013982485154d9d35b35d6d8ec06dd66083dd74a0e2b6766942b8418051b704.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "5021e42829406569d83c4712eca50851ec85eb2c6db68f794cb86251051d2d28", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "64336315cf4583734f32b4d8b9c68256093f105b4e521271ba317d866ede5086", "generation_seconds_batch": 22.448500589001924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011961087584495544, "target_z": -0.42578126377376824, "ce": 5.847874641418457, "genuineness": 4.846253395080566, "identity": 0.6947205662727356, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5021e42829406569d83c4712eca50851ec85eb2c6db68f794cb86251051d2d28.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "507b8ce09f8e1669a1450664aa7996f6037e831c1573edaa169b75cd034147ca", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fdf7acde6268ae6a9a4de04666873bb2933d1977d4646e2069cbb261ccee9ac2", "generation_seconds_batch": 20.011510295094922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.046441555023193, "genuineness": 4.808597087860107, "identity": 0.8059216141700745, "hypothesis": "J'ai trouvé la 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_Shame/507b8ce09f8e1669a1450664aa7996f6037e831c1573edaa169b75cd034147ca.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "509c981ce896c00fb021445b3cb3f697b9008ad4883edace89adebc6107e30a8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19e9c883536dc4fbba21a4c791c992c7a208302fd97f0423aeadcee207d8c911", "generation_seconds_batch": 16.505354143911973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07810510694980621, "target_z": -0.25390624777842447, "ce": 6.054384231567383, "genuineness": 4.20609712600708, "identity": 0.4217597246170044, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/509c981ce896c00fb021445b3cb3f697b9008ad4883edace89adebc6107e30a8.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "512a971545b909bf6a0371d517c03f97144a6cb1414bf16968f4eb456635b328", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "100d3bd0fa9ce5282dbfba9048ebe2f459c3394463fe5974dfdca2d7e3b13641", "generation_seconds_batch": 19.92201441701036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.300607204437256, "genuineness": 4.400654315948486, "identity": 0.40215009450912476, "hypothesis": "The 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_Shame/512a971545b909bf6a0371d517c03f97144a6cb1414bf16968f4eb456635b328.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "5160967724d217e576554cb4723194e6865aa814b4caee633c5347328c244cb3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e22f8a454606f4eee2392be65df9b945c956767a3053bb0ef8ec1425c2eb36f8", "generation_seconds_batch": 21.667133577982895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015031516551971436, "target_z": -0.43164062122332164, "ce": 6.133810997009277, "genuineness": 4.595211505889893, "identity": 0.5553070902824402, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5160967724d217e576554cb4723194e6865aa814b4caee633c5347328c244cb3.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "517f5d8439c9265c759b140c4bc215a2c855c41b38bd076adf04fd3305e04145", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4157628ed82164d541dc4f41f4e3fd1436bbab56d8d8c29600222b3f5b2e92ef", "generation_seconds_batch": 21.178151143016294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 5.085378646850586, "genuineness": 4.15588903427124, "identity": 0.6003620028495789, "hypothesis": "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_Shame/517f5d8439c9265c759b140c4bc215a2c855c41b38bd076adf04fd3305e04145.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "5227b2356c0267b7ba9b883976eff3dc33f901341dbf3400e37d62fdd323cf1b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bc89625927d9700be68fe3ab90a912e40b9cb186f715fd91f5568a44e8221d1d", "generation_seconds_batch": 16.62110972602386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 5.804190158843994, "genuineness": 4.444586753845215, "identity": 0.7405985593795776, "hypothesis": "J'y trouvai la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5227b2356c0267b7ba9b883976eff3dc33f901341dbf3400e37d62fdd323cf1b.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "523ab3aa8c2e3eca913a4d947c752018c682f7abd3744faf721a49e8cb5d1bfb", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "15fe1eb3164ae6d157f76d8e518669e863124dab724008a0c24a276c3b871172", "generation_seconds_batch": 25.341422375990078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.054384231567383, "genuineness": 4.607763767242432, "identity": 0.5921491384506226, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/523ab3aa8c2e3eca913a4d947c752018c682f7abd3744faf721a49e8cb5d1bfb.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "525e4e2637a066e10dbbfd2849c69b1c6be7e7022663043c4c5fc4c987020044", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eb0cc117b4c7d4057f50f08e37952060cfa794b2ca43f6bdf0d03c2e53ea937f", "generation_seconds_batch": 20.502163465018384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.23706579208374, "genuineness": 4.268857479095459, "identity": 0.3022282123565674, "hypothesis": "The 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_Shame/525e4e2637a066e10dbbfd2849c69b1c6be7e7022663043c4c5fc4c987020044.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "52740a0016270dbe2e4c92a66dfcb5e51ed479a3bfa1cf3c95d65c85ca15b8bb", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "059e565373f7c2fe15e723feeb7f673ebfd3da117c5ba50960fe835cb78012f6", "generation_seconds_batch": 16.61384928401094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 5.8875885009765625, "genuineness": 4.6956281661987305, "identity": 0.7913532257080078, "hypothesis": "J'ai trouvé la 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_Shame/52740a0016270dbe2e4c92a66dfcb5e51ed479a3bfa1cf3c95d65c85ca15b8bb.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "532c19e9f23ac01ce68c5cdda9f34238fcc03c46fb09d79e8530d3fb62567698", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6675f7c04e0c9bdef3ea7c12a6deb4c7a18a4e3d66973ff5f962765bad064621", "generation_seconds_batch": 21.484496903955005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0007028132677078247, "target_z": -0.4042968867743503, "ce": 6.292664527893066, "genuineness": 4.444586753845215, "identity": 0.6790929436683655, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/532c19e9f23ac01ce68c5cdda9f34238fcc03c46fb09d79e8530d3fb62567698.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "533230b3bb9234807453c9af605c11e195cd89169fa49f0132b45a358ec3312e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bf22c22bb7e7579980f7d517ba76543de271ea2384823eaa2ebcf81c00e8f6e6", "generation_seconds_batch": 14.942114182049409, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.6257527470588684, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/533230b3bb9234807453c9af605c11e195cd89169fa49f0132b45a358ec3312e.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": "53620a1ca09b4dab870ade8eb5e4a4c859837858c3b8d46e2899dd82010eeaeb", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4528f2e5e4025f98441a3e1bb4848a80c26748619203b48b2d64ce1e17264a1", "generation_seconds_batch": 14.902507689082995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 5.9431867599487305, "genuineness": 4.570107460021973, "identity": 0.5359240770339966, "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_Shame/53620a1ca09b4dab870ade8eb5e4a4c859837858c3b8d46e2899dd82010eeaeb.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "543e3e47a4b56fb6bbf7504460bb2964ce9e56d641da2b4e4a790b3b11523df1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0849fa67c57ed856e15a6882ec41f66a326acc6f8c58e3aea9caa3d8c02fe260", "generation_seconds_batch": 19.937134218984284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.213237762451172, "genuineness": 4.432034492492676, "identity": 0.5979936122894287, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/543e3e47a4b56fb6bbf7504460bb2964ce9e56d641da2b4e4a790b3b11523df1.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "8b7e227b8df5249c470cc1a29cd9ab41c5a13d0c4e58d352924830f3dc98c79f", "generation_seconds_batch": 16.271461609983817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.284721851348877, "genuineness": 3.9550557136535645, "identity": 0.5723271369934082, "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_Shame/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "559c8017ecc6af7b4846f07c2c0bdbd319cea5beadce4279b0f70232a1b570cb", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "98510f6be8b8e3fc09e3be188d7a86d62d9ebc49ebebefa389c277b1239f2c13", "generation_seconds_batch": 24.73696795105934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.149696350097656, "genuineness": 4.7332844734191895, "identity": 0.5801909565925598, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/559c8017ecc6af7b4846f07c2c0bdbd319cea5beadce4279b0f70232a1b570cb.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "55e31cdaedb623e7652639418686ea1ea32bbd93b326fd93dee0d06ce7c2cafc", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1e9495edc902b51f34d80bd74a2e613cf9de68e4af43ba471010689eba648149", "generation_seconds_batch": 21.818518418003805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 6.086154937744141, "genuineness": 4.557555198669434, "identity": 0.6117653250694275, "hypothesis": "De deur staat nog op. 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_Shame/55e31cdaedb623e7652639418686ea1ea32bbd93b326fd93dee0d06ce7c2cafc.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "566a7b09f1a23c83b45aad6d7feb6f1e3bc26f562448f4a5386618fbc393f03d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d0953bbcc8698ac37d9d6c7268936da636dca857ba64f331dc9f12d3e8ae8fe", "generation_seconds_batch": 20.24525788403116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 6.173524379730225, "genuineness": 4.231201171875, "identity": 0.4030422568321228, "hypothesis": "The 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_Shame/566a7b09f1a23c83b45aad6d7feb6f1e3bc26f562448f4a5386618fbc393f03d.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "56804208699b67913ba1a66e2faa3f8ba7c0ecbfc17719e90df04221e44271bb", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8cde84f97a82fd5b0de68451c728748f0e33382c7585a80b1c65822de74e06d6", "generation_seconds_batch": 20.488657042966224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05251811444759369, "target_z": -0.30273438766298044, "ce": 5.796247482299805, "genuineness": 4.582659721374512, "identity": 0.49673494696617126, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/56804208699b67913ba1a66e2faa3f8ba7c0ecbfc17719e90df04221e44271bb.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "56b306ad9c240d4420ac66edae84da43c333235a058b2031796144881f982763", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "47df29c43288af61d08e8bb0f9da497b89c3321b90e9999f92a0a540a06e7611", "generation_seconds_batch": 17.137489440036006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.871703147888184, "genuineness": 4.306513786315918, "identity": 0.2717841863632202, "hypothesis": "The 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_Shame/56b306ad9c240d4420ac66edae84da43c333235a058b2031796144881f982763.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "56cd0fadb10bee376e1208c918bfc91bb2f78eb433f903c4eb0025f99e103750", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6444dfe85b82d26059a8f21174953e255ced1924d4c3d956b1d5188931825341", "generation_seconds_batch": 16.19682778499555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004796728491783142, "target_z": -0.4121093823311992, "ce": 6.165581703186035, "genuineness": 4.432034492492676, "identity": 0.6928483843803406, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/56cd0fadb10bee376e1208c918bfc91bb2f78eb433f903c4eb0025f99e103750.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "57195ef2ecefcafb17b1a74983f8795f5e9fde95e2a7112045ab85ab2fc72a69", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f357e62f03e8c47543b5588d66fe62c7818e9e656c9c31e25cfbc3e252b9ae8d", "generation_seconds_batch": 14.98847919004038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.0305562019348145, "genuineness": 4.7081804275512695, "identity": 0.6846128702163696, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt, Sujit.", "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_Shame/57195ef2ecefcafb17b1a74983f8795f5e9fde95e2a7112045ab85ab2fc72a69.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "5723e92e7044d65a96dec8c55f72bfe3569868e00174f207c7db9a36c7978815", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "824d6051fd63083b24ec310600ea439c66bec03acde68aff752f165bc3550fd8", "generation_seconds_batch": 19.955406173015945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.054384231567383, "genuineness": 4.444586753845215, "identity": 0.6857151985168457, "hypothesis": "J'ai trouvé la 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_Shame/5723e92e7044d65a96dec8c55f72bfe3569868e00174f207c7db9a36c7978815.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": "574a64fc0e877b064fbf4b6dca3b7fb02e52ce1d2b597093eddb0b116469db63", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "0bb65c8547c4be202915a6366f48be1a6ae5a0b2572bd3cd44723333ac77f8c4", "generation_seconds_batch": 15.987172010005452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 6.022613525390625, "genuineness": 3.9425034523010254, "identity": 0.5927311778068542, "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_Shame/574a64fc0e877b064fbf4b6dca3b7fb02e52ce1d2b597093eddb0b116469db63.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "575351f61b81cf48a38a14a73d1de2e2c0082101cd7b25768940f480fcb3f1a0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "873581df0b6398deab16a1d01886e915f07eac442898fecbd89d73bdc72563db", "generation_seconds_batch": 22.24808646691963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016055002808570862, "target_z": -0.43359375933061717, "ce": 5.998785495758057, "genuineness": 4.595211505889893, "identity": 0.6157328486442566, "hypothesis": "La porte 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_Shame/575351f61b81cf48a38a14a73d1de2e2c0082101cd7b25768940f480fcb3f1a0.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "5760805565b7bd71a2320a04778e74eb3541a1a7676a085a722f3aab02041a8b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5cc5fcd1f4ec1681e5ca5f5544ec9d3db7357f8ebf610a4ed5fadfe597643069", "generation_seconds_batch": 24.575039113056846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03345414996147156, "target_z": -0.4667968796653086, "ce": 5.831989288330078, "genuineness": 4.645420074462891, "identity": 0.8065590858459473, "hypothesis": "La porte 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_Shame/5760805565b7bd71a2320a04778e74eb3541a1a7676a085a722f3aab02041a8b.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "57901b9a7fb5543f2ab8c878edb6ef6fbb5fcaffaede5090644ed3ea5bf09f07", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46edf3a16b82b75c10297bc1e5d67afd0e92860d4b45ee94b1d740fd6646acb6", "generation_seconds_batch": 14.85462025902234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 5.911416053771973, "genuineness": 4.300237655639648, "identity": 0.39257216453552246, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/57901b9a7fb5543f2ab8c878edb6ef6fbb5fcaffaede5090644ed3ea5bf09f07.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": "57a61463882b17b4b882b63cbd6cd2c42541551f38ebed21d68bec317e01af17", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d7f93f697f4b8e58fc0063509f592b622db3c8ffc500855b3b894b7d282f8e37", "generation_seconds_batch": 16.636159666930325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 5.689021587371826, "genuineness": 4.406930446624756, "identity": 0.6581766605377197, "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_Shame/57a61463882b17b4b882b63cbd6cd2c42541551f38ebed21d68bec317e01af17.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "57cc8cdcc494789bd81d98a4e3c07a363ff32bc4df7378afaba2bda9593450b0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "56987392b987a08fdfe05c116b8f49da5ba516918cf01d4afe6788ae3360ecbd", "generation_seconds_batch": 20.07251875801012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007485032081604004, "target_z": -0.38867186722448566, "ce": 6.054384231567383, "genuineness": 4.65797233581543, "identity": 0.6961759924888611, "hypothesis": "La porte 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_Shame/57cc8cdcc494789bd81d98a4e3c07a363ff32bc4df7378afaba2bda9593450b0.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": "5811bc4f82a930e353feeba54afa10f5f48755ba1f8f80cd04d51fc91f55ed11", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e275b211cc90717533b86a68dd963517b96665c330bb5febe8fa9d53d2eb1c1b", "generation_seconds_batch": 14.604511679965071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06172943115234375, "target_z": -0.285156258441987, "ce": 5.982900142669678, "genuineness": 4.482243061065674, "identity": 0.8514695167541504, "hypothesis": "Les clai sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Branley quand tu partiras.", "wer": 0.125, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5811bc4f82a930e353feeba54afa10f5f48755ba1f8f80cd04d51fc91f55ed11.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": "598a4f0b1e5348148ae580c74aacb3f001452697f8369a14449b2530eb7bf3cd", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "00903a422bda70fbf5e00e1be2a4b072249b3fb8d95bc568febeccdd812794e6", "generation_seconds_batch": 14.670312038972043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 5.585766792297363, "genuineness": 4.017816066741943, "identity": 0.5863165855407715, "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_Shame/598a4f0b1e5348148ae580c74aacb3f001452697f8369a14449b2530eb7bf3cd.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "5a0e46ce2260c4dbefedb6ad1a985c6b4ce60f715028a7312b6dcccd8eef6a02", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "97278bc55baaf79d333b6ad0e95d6c4902911d5872f4caa05d3714c0e38febc8", "generation_seconds_batch": 21.86093702807557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 6.165581703186035, "genuineness": 4.796044826507568, "identity": 0.81093829870224, "hypothesis": "J'ai trouvé la 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_Shame/5a0e46ce2260c4dbefedb6ad1a985c6b4ce60f715028a7312b6dcccd8eef6a02.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "5a1e495a01de035aae40a1fd305a5e0c28be1b6ab896275de104125b0066df42", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d68eb877ee532a66b3c8915c9c4c0542e4852cb28781af6cf81cb701e58edcd", "generation_seconds_batch": 20.48822614690289, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456508696079254, "target_z": -0.29882811144838933, "ce": 6.197352409362793, "genuineness": 4.607763767242432, "identity": 0.3956361413002014, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5a1e495a01de035aae40a1fd305a5e0c28be1b6ab896275de104125b0066df42.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "5b341a70bb199b28b7896bcd1d5f5e040b1e0ed6edb114c0fb40bf82b45f5b69", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "48df2f482b7079ef00472bbd9330fc8ab431dd06920482a87f4bda193770fe37", "generation_seconds_batch": 16.68988438800443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016055002808570862, "target_z": -0.43359375933061717, "ce": 6.41180419921875, "genuineness": 4.507347106933594, "identity": 0.39728957414627075, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5b341a70bb199b28b7896bcd1d5f5e040b1e0ed6edb114c0fb40bf82b45f5b69.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "5b4ff97087c2578f75f062d0c40a91af2284b3b64fe51c03d4f89ab73935064b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b65f6cea46e65bb07de3f001a667e34d8c450a7cee9c3d8679057512ff447f3e", "generation_seconds_batch": 16.048846506979316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 5.601652145385742, "genuineness": 4.356721878051758, "identity": 0.6102322340011597, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5b4ff97087c2578f75f062d0c40a91af2284b3b64fe51c03d4f89ab73935064b.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "5b8e3f03c454c2ee5fe077bf0a5d5cbb81dd1a48ec16a56524b7edded9128eae", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b6f5fdcab9c9b0b306a925a9ad9e27194f1d8999be36c651be47ac39950f58e0", "generation_seconds_batch": 20.469838181044906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08629293739795685, "target_z": -0.23828125666472655, "ce": 5.919358730316162, "genuineness": 4.68307638168335, "identity": 0.47012871503829956, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5b8e3f03c454c2ee5fe077bf0a5d5cbb81dd1a48ec16a56524b7edded9128eae.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": "5be3ebd0d65bcd13c38898db08805cabfd5af14f2567f3ccde2ee364c8ed4066", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2d703f29792896d28d16f4e4160060614c8643a59081be69a637931faa2c212d", "generation_seconds_batch": 23.971455091028474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 5.681078910827637, "genuineness": 4.105680465698242, "identity": 0.7619199752807617, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5be3ebd0d65bcd13c38898db08805cabfd5af14f2567f3ccde2ee364c8ed4066.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "5be45773ba4ac25a6cc214a8bc734af951f34431cd0157e6f335de704028435c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e62c7fd28091785dcc75b662673262edfc35bcc7b5350e3ea049e40e7a72d49e", "generation_seconds_batch": 23.757029858999886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 6.046441555023193, "genuineness": 4.243753433227539, "identity": 0.5296294689178467, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5be45773ba4ac25a6cc214a8bc734af951f34431cd0157e6f335de704028435c.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "5c56a8d5192da92ce99b9deb05a412ca5a9c433f0df1c686107ac170da06c348", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e7b1bb7186a6da3500cb7a21be080638d58e8d654aa2f7eb40c72658af3e5ccc", "generation_seconds_batch": 20.57940004300326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.165581703186035, "genuineness": 4.582659721374512, "identity": 0.5278058052062988, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5c56a8d5192da92ce99b9deb05a412ca5a9c433f0df1c686107ac170da06c348.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": "5cf72c908629f25835fd5f96f00aefa003264b5621fa4f25a31fc71a08c80348", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "0fbfb7d1789446a79e17d49e52c99a09c88d0465777cac1ee5893e2f2ece0a15", "generation_seconds_batch": 16.42840678000357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07298770546913147, "target_z": -0.26367188144256903, "ce": 5.601652145385742, "genuineness": 4.005263805389404, "identity": 0.7451148629188538, "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_Shame/5cf72c908629f25835fd5f96f00aefa003264b5621fa4f25a31fc71a08c80348.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "5d36f481508137465658ba1e3381b150f6fb39b4916d28fc8f1524715572f113", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9bbff33619c8aaf5addda179109e719927e806223807411ffd3ffa94c34f5b75", "generation_seconds_batch": 20.636024457984604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053541600704193115, "target_z": -0.3007812495556849, "ce": 6.0146708488464355, "genuineness": 4.68307638168335, "identity": 0.37713122367858887, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5d36f481508137465658ba1e3381b150f6fb39b4916d28fc8f1524715572f113.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "5d3ec3c4a4516b26c396647127224a43a27821b925d555d30bbbc9bf55e1cd2f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0e8eed3f2d1aef1229a3fbc8b077b4c2c10afa9d68b8be962767c85190350a73", "generation_seconds_batch": 22.448500589001924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 5.470598220825195, "genuineness": 4.6203155517578125, "identity": 0.5757109522819519, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5d3ec3c4a4516b26c396647127224a43a27821b925d555d30bbbc9bf55e1cd2f.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": "5d636865c703b6aa4a33ba8847b7b8c2be01cb1f5c1bf28523132f4435b458bd", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "e49672c6a4d617f478c9e9d6b6f5b188059241ab3f5fcde65e5e2ec2dafc5ca6", "generation_seconds_batch": 18.09070794598665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04637724161148071, "target_z": -0.3144531309982539, "ce": 6.125868320465088, "genuineness": 4.281409740447998, "identity": 0.36150431632995605, "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_Shame/5d636865c703b6aa4a33ba8847b7b8c2be01cb1f5c1bf28523132f4435b458bd.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "5db77e360a77586b69eec475464d788a819f0e13e019f0d9f50f5ced76470a4a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b3bf1645c08125b373b091025954e4ba72df3c05354fed684c64ebf5e0d0c27", "generation_seconds_batch": 24.236359754926525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 5.935244083404541, "genuineness": 4.300237655639648, "identity": 0.1921331286430359, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5db77e360a77586b69eec475464d788a819f0e13e019f0d9f50f5ced76470a4a.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "5df39f9c85013a646a8fa515b85221cdb6e2794af8ef633f563141ff5ba29391", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "30fd2bc2fcf05a2cf4d12e222e6e453c4c577a7c8085d46f3e69910b8a54fc98", "generation_seconds_batch": 20.46953083400149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 6.324435234069824, "genuineness": 4.758388519287109, "identity": 0.5877484083175659, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5df39f9c85013a646a8fa515b85221cdb6e2794af8ef633f563141ff5ba29391.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "ce08f160480cb6494ba3f54a5c8917b88adb7665234f1a0b88d81f112294dc60", "generation_seconds_batch": 14.939674741937779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 6.086154937744141, "genuineness": 4.306513786315918, "identity": 0.7852933406829834, "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_Shame/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "5e22c5ec6230b0a8a735fa810f2476dd22677a0b38bace88a70d5af115f2276b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c3157f6708860f7acc5d55042ff71e50e35560730b21c458a3226ac1035aa6fd", "generation_seconds_batch": 22.043553980998695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 5.839932441711426, "genuineness": 4.607763767242432, "identity": 0.6525512933731079, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5e22c5ec6230b0a8a735fa810f2476dd22677a0b38bace88a70d5af115f2276b.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "5f40c2b41f3f68157b49f5300d63805ba4014c99338f1cc0ced90a57b9aef16f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "aee28a9b85986f0a58e6de86286fc189e4d7fb35e4dbd99be4cf43dfcc3be38a", "generation_seconds_batch": 22.781461987062357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.7584712505340576, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/5f40c2b41f3f68157b49f5300d63805ba4014c99338f1cc0ced90a57b9aef16f.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": "5f894a420e082dc587e5532c09a090d6cf928d0c9aa159e0a899e66b60962927", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c732798f624e66e2c6d5e2d78769f9ae9bce39362f160334d0709faf70f53d55", "generation_seconds_batch": 14.832779667922296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 5.990842819213867, "genuineness": 4.406930446624756, "identity": 0.7637003660202026, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relubi. J'ai rangé mon téléphone. Dis-moi, quand nous pourrons parler ?", "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_Shame/5f894a420e082dc587e5532c09a090d6cf928d0c9aa159e0a899e66b60962927.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": "604bd9c135a9873b1a2f3702c6c3ae638fd79c6b8aeb60897772c09922be5b7d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9241a42ac129b1f38f5de3136d2e82880788d12500d8847127231e2e7c0cbb9a", "generation_seconds_batch": 23.742165685049258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.657250881195068, "genuineness": 3.9927117824554443, "identity": 0.6020419597625732, "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_Shame/604bd9c135a9873b1a2f3702c6c3ae638fd79c6b8aeb60897772c09922be5b7d.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "604fa264299ba6a702b77721fc3f1799ef9af536fbd7de61fa2276a182d0f3f4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7744001d6b2ce06daacf5a91d1aa7953d724b7275a7b28190fb3e0f22a893014", "generation_seconds_batch": 20.898360453080386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.197352409362793, "genuineness": 4.162164688110352, "identity": 0.23591120541095734, "hypothesis": "The 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_Shame/604fa264299ba6a702b77721fc3f1799ef9af536fbd7de61fa2276a182d0f3f4.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "606795385077eedf3c30f64a0fce2832bb713d2f85c5f3ee39ad55a360c1c956", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "587c4e8ae19b6b96be0780633e5c377944c0e86d2021b4758b9c524276ce7a1b", "generation_seconds_batch": 22.598938719951548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 5.911416053771973, "genuineness": 4.507347106933594, "identity": 0.2361723929643631, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/606795385077eedf3c30f64a0fce2832bb713d2f85c5f3ee39ad55a360c1c956.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "60a09e6c9c6c7415a639b44d664525cf57d3578bbcbd2fdf5a91fd25192c8017", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a4b87a84a8b7f64227e128e896b698d613476bdff0ec76647010e3c2935c7549", "generation_seconds_batch": 20.4205835449975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006843686103820801, "target_z": -0.4160156301096237, "ce": 6.348263263702393, "genuineness": 4.444586753845215, "identity": 0.32052645087242126, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/60a09e6c9c6c7415a639b44d664525cf57d3578bbcbd2fdf5a91fd25192c8017.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "60b0d87f51d81aa09d5c761b861d895d280dc250634aea7838944ec076cd0653", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a3dd0d9857ae3554b2cfc8c2e014e512b2970d05c39e5303dd72cc7586ebb33b", "generation_seconds_batch": 20.372393694939092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 5.6413655281066895, "genuineness": 4.557555198669434, "identity": 0.5275038480758667, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/60b0d87f51d81aa09d5c761b861d895d280dc250634aea7838944ec076cd0653.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "61036770d7482b3b10a2e0ad44d459d73aa651ca3e93a0967a2b8db896a84eb2", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3235416e5230f198dafdd9061aa26a128f471ff6616e16f4e6919986f5584c61", "generation_seconds_batch": 20.534617764991708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 6.09409761428833, "genuineness": 4.3881025314331055, "identity": 0.40236300230026245, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/61036770d7482b3b10a2e0ad44d459d73aa651ca3e93a0967a2b8db896a84eb2.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "61114a07589f6e4b7d0cf39f79931cc551db6ec171049ee3afc68133c5cfe46d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7d5ac7e2e7858b8c390debbc5f101639b91922be63307f1feb518c69e96f5e70", "generation_seconds_batch": 17.137489440036006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01810196042060852, "target_z": -0.4375000071090417, "ce": 6.173524379730225, "genuineness": 4.607763767242432, "identity": 0.4520752429962158, "hypothesis": "The 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_Shame/61114a07589f6e4b7d0cf39f79931cc551db6ec171049ee3afc68133c5cfe46d.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "615f0a0a87b0b44dfd0b37029a413a3b13faadf148a3bd61c6f7456503801f47", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fe456582730bfece7ea589b32f5176666f2d9ad4ac4ab7ab9eb921a9c3974c62", "generation_seconds_batch": 20.98018349497579, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.990842819213867, "genuineness": 4.557555198669434, "identity": 0.6242045760154724, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/615f0a0a87b0b44dfd0b37029a413a3b13faadf148a3bd61c6f7456503801f47.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "61f16920169d28ee2108f4be43c5f8b5ab6a72720c153892ba7153ef8fb19e51", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "be5a97afba4a879565566521885a24df9f9f31106469ad91c398115799613e59", "generation_seconds_batch": 18.068825416034088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 5.903473377227783, "genuineness": 4.7834930419921875, "identity": 0.5825847387313843, "hypothesis": "Mais 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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/61f16920169d28ee2108f4be43c5f8b5ab6a72720c153892ba7153ef8fb19e51.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": "61f4325a260f6f4d3a29633963a5d5c05952a5aae6fcc974d01249293b1ef80c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "842eff221f4a1e7853e214aa41fbc63d3b7001ca2ec6fc0326329a5c41b14756", "generation_seconds_batch": 18.003607311984524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.903473377227783, "genuineness": 4.281409740447998, "identity": 0.638807475566864, "hypothesis": "Tu mensaje hijo después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/61f4325a260f6f4d3a29633963a5d5c05952a5aae6fcc974d01249293b1ef80c.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "6218de82a41109b04b531663362a44c20dc86a10c273f327e0f4d2713cfc2d72", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "53fec9fc453bf23d020a39227193b9c9da103515e6e977f42c60230c0e2b8288", "generation_seconds_batch": 20.3818281639833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.125868320465088, "genuineness": 4.7332844734191895, "identity": 0.7670531272888184, "hypothesis": "J'ai trouvé la 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_Shame/6218de82a41109b04b531663362a44c20dc86a10c273f327e0f4d2713cfc2d72.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "62414974364eb559c253b15ed86668ca78285886145891b9095337bb35e9c1fa", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ba4c792d710ba049e9d6750d1d79fe3a94c425352846c211cb6122336f87c08e", "generation_seconds_batch": 20.085721159004606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 5.474569320678711, "genuineness": 4.268857479095459, "identity": 0.48003947734832764, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/62414974364eb559c253b15ed86668ca78285886145891b9095337bb35e9c1fa.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "62a6621f649449c54309436150683f44232859093569ae7342c4cc2cc83b1da6", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "69fe0c7accad8d49d01a66b1b4c1e78094258fb7f1289b25768b9db138e5eb2b", "generation_seconds_batch": 16.1557211400941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.292664527893066, "genuineness": 4.545003414154053, "identity": 0.6316209435462952, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/62a6621f649449c54309436150683f44232859093569ae7342c4cc2cc83b1da6.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "634987d842c4ff562aef520d6cb887d8d9c6d681553422127533c6fdde8f0c5a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "20d16ce8bb0fdc6c682aba784329e4aeded4265d884031b8b071547325e99ef2", "generation_seconds_batch": 20.411190609098412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004796728491783142, "target_z": -0.4121093823311992, "ce": 5.998785495758057, "genuineness": 4.645420074462891, "identity": 0.5301240682601929, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/634987d842c4ff562aef520d6cb887d8d9c6d681553422127533c6fdde8f0c5a.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "6359507aa1611f99a2ea3424a4e930c60a490e1829deecd0cb80a1f54ebcb0f8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8fe3d71b9df4f955e35fd5ad9ec6d0b398ed6a542c187e01adee52a9ce9a637d", "generation_seconds_batch": 14.77726627397351, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 5.788304805755615, "genuineness": 4.808597087860107, "identity": 0.5354903936386108, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6359507aa1611f99a2ea3424a4e930c60a490e1829deecd0cb80a1f54ebcb0f8.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "63597e119f4565ffc7390b8890f35d109d0b710979a51e4a20fb299b84d3bb5e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a589ef5d2a75baedc6f833d94ccb0465425dd247cf7881fe00cc996a83a4dd65", "generation_seconds_batch": 21.256263831979595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.0146708488464355, "genuineness": 4.482243061065674, "identity": 0.7741702795028687, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/63597e119f4565ffc7390b8890f35d109d0b710979a51e4a20fb299b84d3bb5e.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "635bb96c83fa674e4cc9e66d54dd457e01bc2f348b962c614b2d682b07aaffcc", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "dc38eae698b1e326f311d8a3ce867fc75a7614f8d3798cbca78146c1f2c8a204", "generation_seconds_batch": 21.46534316893667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 5.4666266441345215, "genuineness": 4.262581825256348, "identity": 0.49881213903427124, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/635bb96c83fa674e4cc9e66d54dd457e01bc2f348b962c614b2d682b07aaffcc.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": "63bfc53b760e0eca62f4e4ca6cdad0bde3b1c999fee20a37d3a51cc2f4333ab6", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64062b78dbb12dba5ec6a91faf2d64415e8a2571d0941fa6a27fadcb048cd219", "generation_seconds_batch": 20.22340640099719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 5.95112943649292, "genuineness": 4.268857479095459, "identity": 0.458381712436676, "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_Shame/63bfc53b760e0eca62f4e4ca6cdad0bde3b1c999fee20a37d3a51cc2f4333ab6.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "63c484f86716e7cf097c47f6eb30090bed071e1fd3ff7de14a0491999e2613f4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "35d82d77a768b45c9d96544edd2066d2228f8109e6e57510b3c5c8a3505d809d", "generation_seconds_batch": 20.179360706009902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.967014789581299, "genuineness": 4.519899368286133, "identity": 0.5847792625427246, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/63c484f86716e7cf097c47f6eb30090bed071e1fd3ff7de14a0491999e2613f4.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "643cdaba838f73d5841c47fce942798e348a169afefde3ee2072929aad959d10", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d9efb3775f403be97c33416d50862a488d27a80ea3e00e23bb23c233f5d07b4f", "generation_seconds_batch": 17.828152089030482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 5.542081832885742, "genuineness": 4.557555198669434, "identity": 0.5962766408920288, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/643cdaba838f73d5841c47fce942798e348a169afefde3ee2072929aad959d10.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "6440e31ea5ec45584e46494d8a37c7e48a6fa4f90e63a1adcb6b5d246838048d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a845d146bfeee7572f8b6b819ca55055426e689096cab40192b1fb8faa17d9f2", "generation_seconds_batch": 17.298354084021412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.1020402908325195, "genuineness": 4.68307638168335, "identity": 0.8408968448638916, "hypothesis": "J'ai trouvé la 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_Shame/6440e31ea5ec45584e46494d8a37c7e48a6fa4f90e63a1adcb6b5d246838048d.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "64c9e60105128b2584090ab1cfec20219d5eacc447d322b13241cce98b75260f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "823508c1e4d561e5be0c9f5ed221879404f64dda8ec991ddb4e7dbb56e118a45", "generation_seconds_batch": 20.040366685017943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.268836498260498, "genuineness": 4.344170093536377, "identity": 0.4411989450454712, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/64c9e60105128b2584090ab1cfec20219d5eacc447d322b13241cce98b75260f.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "65819ce4246d8a6b18965cf8838d26409281e254367f25ae94eaae7d420f087d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "18dbcc9b8e522f41de97f682a2c53c17b361e16de5bc817df7f406cc4dc7aebf", "generation_seconds_batch": 21.667133577982895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 5.911416053771973, "genuineness": 4.7332844734191895, "identity": 0.5435524582862854, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/65819ce4246d8a6b18965cf8838d26409281e254367f25ae94eaae7d420f087d.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "6595baf154e8650a64b52d82e40337e96117f948da5d8107506675feb5e6582a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbb0957af846ea5d4a487ffedd3d5c0cfa6c52101eb3ad5b41914ffdf2668f23", "generation_seconds_batch": 20.372393694939092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.109982967376709, "genuineness": 4.971774101257324, "identity": 0.6514744758605957, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6595baf154e8650a64b52d82e40337e96117f948da5d8107506675feb5e6582a.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "65cfb18c29c3cfca6d9d54afc102a5a3f9360615ab96db69eff56222d3a3d481", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5f0b3c4f3f3cd99fc6fa5b36c6b9b01fb5a7f674f695681523fad3ba3cace652", "generation_seconds_batch": 19.878354945103638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.2767791748046875, "genuineness": 4.6203155517578125, "identity": 0.8090839385986328, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/65cfb18c29c3cfca6d9d54afc102a5a3f9360615ab96db69eff56222d3a3d481.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "661e2de66d86f120c300f81110f9b3254191f0267c42c139e03336e8a6d35be1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "461bd77722e668f9503dedaabbca0c574f90636ca60eb325fa91bcc0ef09f0e8", "generation_seconds_batch": 20.87786117300857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.006728172302246, "genuineness": 4.444586753845215, "identity": 0.5032016634941101, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/661e2de66d86f120c300f81110f9b3254191f0267c42c139e03336e8a6d35be1.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "662a9775fdc4b1662ba9fd01d009c9e818a3b503dfb6c168c109ff189a0baf9e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9e04df28474019942c2073dff8067cc04770531d85712805078d3529787a394d", "generation_seconds_batch": 20.625214640051126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 5.911416053771973, "genuineness": 4.469690799713135, "identity": 0.674323558807373, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/662a9775fdc4b1662ba9fd01d009c9e818a3b503dfb6c168c109ff189a0baf9e.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "67067f6cb15b8df9f3029ff6bd5d5406f73e23991e2f732b17cdb183e8920f90", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4eae7c6648d378d9e2523e55f032ecb6fa790d4acb417ea2e0d6b2bd38d3f720", "generation_seconds_batch": 21.125720162992366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.340320587158203, "genuineness": 4.256305694580078, "identity": 0.5679027438163757, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/67067f6cb15b8df9f3029ff6bd5d5406f73e23991e2f732b17cdb183e8920f90.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "6733efffe8a9d74bbca858930584a19533c70cbbe786889ccfcde60da3d789db", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "560a1303667fdb981f49877a72733a0f9b13221deed16f8c22c853c6428d3935", "generation_seconds_batch": 20.450252205017023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 5.839932441711426, "genuineness": 4.808597087860107, "identity": 0.7469729781150818, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6733efffe8a9d74bbca858930584a19533c70cbbe786889ccfcde60da3d789db.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "6857709973644b6a59b79c0650d477bdae245f59d4beeaa90163a0b4177fb6d3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "33b3ce175fc2c103f111cb362287e1bb150289609901967de29aa6a166a7229e", "generation_seconds_batch": 20.019999742042273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 5.927301406860352, "genuineness": 4.65797233581543, "identity": 0.6025477647781372, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6857709973644b6a59b79c0650d477bdae245f59d4beeaa90163a0b4177fb6d3.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "68827cce495b8e8db75acdb24dae1fa2d17506037957c8c26add9fb0fc1ba917", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "05db8b43ebaed6918b2d33150749ae3a04a625db9ce219291d65d995c2560437", "generation_seconds_batch": 20.53731897904072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 6.022613525390625, "genuineness": 4.469690799713135, "identity": 0.7757000923156738, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/68827cce495b8e8db75acdb24dae1fa2d17506037957c8c26add9fb0fc1ba917.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "68e7120685a842ab735fafeebc333a46b2241e9cc76c06a0c306ec70afc44228", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d92a943b3bf1ef3c9eb551ed2299f5e849bcdb89ed5bede921c583a84fe681a6", "generation_seconds_batch": 17.635370356962085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.340320587158203, "genuineness": 4.256305694580078, "identity": 0.48985111713409424, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/68e7120685a842ab735fafeebc333a46b2241e9cc76c06a0c306ec70afc44228.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "690c224408487452824a0e473df51ed45102b8fe4d115ac09ab0e33b49b12ce5", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb11abf77e06ecfaaf0e95e44fdedf6026b6ef9c6b4955534a142fc281839614", "generation_seconds_batch": 18.171159082092345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055588558316230774, "target_z": -0.2968750017772604, "ce": 6.125868320465088, "genuineness": 4.545003414154053, "identity": 0.5345808863639832, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/690c224408487452824a0e473df51ed45102b8fe4d115ac09ab0e33b49b12ce5.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "695b8a72e7f707fcbc31d6b81ebd821a32dcc51181d41032b1283e77a0220bc6", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dba3c79a6f35e06bf2e2f45921f1f98a752f33f8bb71b6e8d6cda81af8e53397", "generation_seconds_batch": 14.837241639033891, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05904112756252289, "target_z": -0.515624991113698, "ce": 5.7406487464904785, "genuineness": 4.595211505889893, "identity": 0.7741901874542236, "hypothesis": "La porte 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_Shame/695b8a72e7f707fcbc31d6b81ebd821a32dcc51181d41032b1283e77a0220bc6.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": "697b5fd6a2c5068859a59bf37b8bdc60281f7407ffb9c7354b4922ccae7e8b7f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "5827d12c37d1647d6d1a3fd101d24afb92da8ba1def71c73ecdf94c1484723aa", "generation_seconds_batch": 14.868079744977877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.645336627960205, "genuineness": 4.494794845581055, "identity": 0.608700156211853, "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_Shame/697b5fd6a2c5068859a59bf37b8bdc60281f7407ffb9c7354b4922ccae7e8b7f.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "6980bac11f807c70bab884ffa16ef1be1d6a899193d03dd4e300a617dafbc09e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b0ed6375cba83f53294965e0256ba65e55830052109fca4285a579d5f2235c9a", "generation_seconds_batch": 23.109273437061347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 6.006728172302246, "genuineness": 4.381826400756836, "identity": 0.620690107345581, "hypothesis": "Ik heb het kleine doosje gevonden, stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6980bac11f807c70bab884ffa16ef1be1d6a899193d03dd4e300a617dafbc09e.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "698bcfcab6174768b63a044d3b6b25706095a2e6cf5668364549eab24b321c8f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7fed46b8fe167d6146ee081b2de4bb7365071b06f2e62b7a2a2d4ee4976e8cc0", "generation_seconds_batch": 20.546278005000204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007485032081604004, "target_z": -0.38867186722448566, "ce": 6.324435234069824, "genuineness": 4.519899368286133, "identity": 0.5502948760986328, "hypothesis": "I found the box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/698bcfcab6174768b63a044d3b6b25706095a2e6cf5668364549eab24b321c8f.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ed627ba1f08acd9f414fb10706dc41a258049554a904b8f94f34772330bbb1d2", "generation_seconds_batch": 16.70099613198545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.41180419921875, "genuineness": 3.8546390533447266, "identity": 0.1890975832939148, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "6aad242fa779c6cac558dd1badd7a499666b88c6e9e2956b453e500f0c45ef39", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "110b1ad9219084e24a6ebd2fb95fbeb2de48fda78146392a988b49f7d57049e8", "generation_seconds_batch": 20.469838181044906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 5.95112943649292, "genuineness": 4.7458367347717285, "identity": 0.5323011875152588, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6aad242fa779c6cac558dd1badd7a499666b88c6e9e2956b453e500f0c45ef39.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": "6b466dd1eaec8bd37f5b2864ab72a9f3b855f2c175cb8869f0588a1380090d2f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "b9bf4d7f909d7cad27589d7badad08df1296c3a138d9d87a3e1d22df27e5639f", "generation_seconds_batch": 14.457030951976776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 6.117925643920898, "genuineness": 4.262581825256348, "identity": 0.6684516668319702, "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_Shame/6b466dd1eaec8bd37f5b2864ab72a9f3b855f2c175cb8869f0588a1380090d2f.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "6b56a2cdff3a8bdddc968ea59a2a9ffc97c06b36e634679c8775ef36ce6b7a3c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "94e6dee807d9f863bce154da2fe707d9c45d0a80ba9b8a300d13219c88b5d872", "generation_seconds_batch": 20.522291789995506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.205295085906982, "genuineness": 4.362998008728027, "identity": 0.48176074028015137, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6b56a2cdff3a8bdddc968ea59a2a9ffc97c06b36e634679c8775ef36ce6b7a3c.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "6b8d72946a35be9f324acb6d2ca236f1829570e139b3ea2e74bd5ae18c0e3598", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c99291fb1f9cb63c19845f9dd71feca5bde63591b1c11a3c2078e0e0540fe02f", "generation_seconds_batch": 22.181434343918227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 5.903473377227783, "genuineness": 4.6203155517578125, "identity": 0.7793888449668884, "hypothesis": "J'ai trouvé la petite gloite. 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_Shame/6b8d72946a35be9f324acb6d2ca236f1829570e139b3ea2e74bd5ae18c0e3598.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "54ad5a2ada1e773456088990cc71260e3d423b2cbc9d2d4eac52e1181a239824", "generation_seconds_batch": 16.49546048103366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.292664527893066, "genuineness": 4.582659721374512, "identity": 0.7519605159759521, "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_Shame/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "6bf5bd78ae1c2b2dee287f0d6366864435e4c98698655b53d11049c0baffcdeb", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8968681d91b38e9e65cad1335f9fa9fe2137c8275171c30e25fdfca934e991c6", "generation_seconds_batch": 20.792251054081134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05251811444759369, "target_z": -0.30273438766298044, "ce": 5.816103935241699, "genuineness": 4.6705241203308105, "identity": 0.8256179094314575, "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_Shame/6bf5bd78ae1c2b2dee287f0d6366864435e4c98698655b53d11049c0baffcdeb.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "6c7a1503a5bbd20032624316a353f10b060e972820344746db1015057a06843d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "be9575d28e23f7f065c7b655c3181608df2d298bca54fc88f74284de0ebfda99", "generation_seconds_batch": 24.588732608011924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05047115683555603, "target_z": -0.30664063544140496, "ce": 5.967014789581299, "genuineness": 4.595211505889893, "identity": 0.6650943160057068, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6c7a1503a5bbd20032624316a353f10b060e972820344746db1015057a06843d.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "6cec591a24bbd487f805b9165f83054b0a7ffdb26701887a0eb99eb534607890", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dceaec54ebfb19d270551624ca756edbea485f631b43f39bcea7fc32a3deb682", "generation_seconds_batch": 24.575039113056846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.2938737869262695, "genuineness": 4.557555198669434, "identity": 0.5731145739555359, "hypothesis": "La porte 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_Shame/6cec591a24bbd487f805b9165f83054b0a7ffdb26701887a0eb99eb534607890.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "6d04da4525b834ab787a7abaab624124fa80a81757e8620510409e39bbc9f3a5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0bed1e213c5699ab30b3302b35dad8ac590b054749ffa07c4e72962297aaaa15", "generation_seconds_batch": 20.72316019597929, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 6.0305562019348145, "genuineness": 4.6203155517578125, "identity": 0.699609637260437, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6d04da4525b834ab787a7abaab624124fa80a81757e8620510409e39bbc9f3a5.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "6d3d702ac0382a68ec490cea01c41f8e303386b04250bc40e2397077d1eedff8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "085fe65d66e3ee383263385eefc68264a001793d025c7079b76384e768314d79", "generation_seconds_batch": 21.08082812698558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 5.935244083404541, "genuineness": 4.319066047668457, "identity": 0.6290566921234131, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6d3d702ac0382a68ec490cea01c41f8e303386b04250bc40e2397077d1eedff8.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "6d56b6e3e70d8c909f0eac04d24112a879f3dc2882ab357cbce94b921a708bcb", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b532b7edaba3a67710b3a1ef2755019fe370007dd96b9a37cdfb6a06a4bcbdd8", "generation_seconds_batch": 20.25057317991741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.149696350097656, "genuineness": 4.7834930419921875, "identity": 0.40019774436950684, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6d56b6e3e70d8c909f0eac04d24112a879f3dc2882ab357cbce94b921a708bcb.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "6e2250ebaa482a83345eacc05e2d2c234bd08047333a975b6f756aa355a880e7", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dc3d240bbf06f4e4a4cfcf47c141d1c785093b78628fc6eddfbaba53215c7288", "generation_seconds_batch": 15.796051323995925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.839932441711426, "genuineness": 4.494794845581055, "identity": 0.7117540836334229, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6e2250ebaa482a83345eacc05e2d2c234bd08047333a975b6f756aa355a880e7.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "6e374bfe4bff489c475f1f5fe0bd49992fc352e6919b88851f75abf2a577722f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "52c6d6c47a773a75ee088a0276ecfbef3b1bae65d2e682a8a469fc9b55b4548b", "generation_seconds_batch": 20.90941343002487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 5.9431867599487305, "genuineness": 4.2751336097717285, "identity": 0.5565019845962524, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6e374bfe4bff489c475f1f5fe0bd49992fc352e6919b88851f75abf2a577722f.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "6e60fdb8bf45a2302254b33daff117150ad6fa49b0aea3efb5a59e57bd5331fc", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "62bc56ac620e859ac6fde012876fdc29c977f5602c9868cc544d445e8e6b6018", "generation_seconds_batch": 21.475104095996358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.4672467112541199, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6e60fdb8bf45a2302254b33daff117150ad6fa49b0aea3efb5a59e57bd5331fc.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": "6e68fba52d334617c7508f4898a8391ca64ff1e2c2378a38e019b63439c72d0e", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e4c6da6f733897337facf815af80ec90c050b08f012e40af1fd32e94be97ef2b", "generation_seconds_batch": 23.742165685049258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.756534099578857, "genuineness": 4.281409740447998, "identity": 0.7085119485855103, "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_Shame/6e68fba52d334617c7508f4898a8391ca64ff1e2c2378a38e019b63439c72d0e.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "6e6d31a4e0aa34c395fb51a208be6eb58d6afcfaf3ddd9f29af29cd030230f6a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6fbbe10169f0d682c3ef5f0f8967c4420ecbf8c2b8985de5fc872fd497281ed8", "generation_seconds_batch": 22.24808646691963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015031516551971436, "target_z": -0.43164062122332164, "ce": 5.831989288330078, "genuineness": 4.7332844734191895, "identity": 0.8043712377548218, "hypothesis": "La porte 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_Shame/6e6d31a4e0aa34c395fb51a208be6eb58d6afcfaf3ddd9f29af29cd030230f6a.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "6ec612d67cc3ee1db219160b0dc6942f62a5d3421247170d9c5e68b04c68fcaf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cb9d4e0f2d11badaeeebe042b403977a0e2a3ef6f669634db966e75de73fab54", "generation_seconds_batch": 20.03495441004634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.292664527893066, "genuineness": 4.243753433227539, "identity": 0.4740673303604126, "hypothesis": "The 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_Shame/6ec612d67cc3ee1db219160b0dc6942f62a5d3421247170d9c5e68b04c68fcaf.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "6f26708bd710ce97353d32860c240de7cdbe8c90ecb167ebf616aa5f6779e3b0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8dbf1daaf67984c2b0c6d14ebeded225a1841cccc794b5ca8fc24012ccf1ddbe", "generation_seconds_batch": 20.10425465996377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03818941116333008, "target_z": -0.3300781221119518, "ce": 6.0146708488464355, "genuineness": 4.406930446624756, "identity": 0.4928283095359802, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6f26708bd710ce97353d32860c240de7cdbe8c90ecb167ebf616aa5f6779e3b0.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "6f2e953ae3c9f2893c79af5038814380e31260f0a063f56eec2d8e802267c321", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d2debbe559cb7a8807f708304889c94b2e9319621c141cefac3b14fb4e621480", "generation_seconds_batch": 20.522291789995506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009914115071296692, "target_z": -0.4218749875591771, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.6314922571182251, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6f2e953ae3c9f2893c79af5038814380e31260f0a063f56eec2d8e802267c321.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "6f8086c83ece08cad8cbef774dc0dc9c73a692a41daca9934b71aa46b8771a90", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "69df49c28b88e490fd85571fb4aea162174d61af5aca01bbcdc8cb5170ea3c3b", "generation_seconds_batch": 16.297621017089114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.4055551588535309, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6f8086c83ece08cad8cbef774dc0dc9c73a692a41daca9934b71aa46b8771a90.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "6f97fb845185e0950b20bc0eaab4f3c880411cfcd2aa2b91a4886774407b66ff", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c107f928d2edaeb578f1e13267c4c222707c789384b4c2a2544282a87bf78a7a", "generation_seconds_batch": 23.3943360990379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 6.324435234069824, "genuineness": 4.482243061065674, "identity": 0.5391215682029724, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/6f97fb845185e0950b20bc0eaab4f3c880411cfcd2aa2b91a4886774407b66ff.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "70cfb13dcec13b63ab8a9293f7ffd50b08c3df78d72ea93f33253ce13bed065d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f6fc3d030c1891f8b3fb9db1f9ced8716a0f4e67501f9d728dd1e2dc64408e6f", "generation_seconds_batch": 14.83172098104842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 5.982900142669678, "genuineness": 4.808597087860107, "identity": 0.8257819414138794, "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_Shame/70cfb13dcec13b63ab8a9293f7ffd50b08c3df78d72ea93f33253ce13bed065d.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "710bda61e11e4696d5cac18093cd2f05ca87711aa933e27e53d183127510a422", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8d020632eced2ea86fb81904df24adf253a433c8f554a2a5684a8fcb59f52374", "generation_seconds_batch": 24.673413568059914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.760505676269531, "genuineness": 4.331617832183838, "identity": 0.5626305341720581, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/710bda61e11e4696d5cac18093cd2f05ca87711aa933e27e53d183127510a422.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": "71499085969d274a6fe518da5dd7e7a7fbeea733940a96dbb598b12b99b90f5b", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "a98ccf47f762ce921de4636250907101143a4d4e32a4f828e621148b830bdad6", "generation_seconds_batch": 17.096597386989743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 6.09409761428833, "genuineness": 4.394378662109375, "identity": 0.3314483165740967, "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_Shame/71499085969d274a6fe518da5dd7e7a7fbeea733940a96dbb598b12b99b90f5b.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "715c9c4803288940b06de9410bafcad0ef3176283b6af223102c8fbd84a56080", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f2f5b33381394f444f5015e609e1901edc256c109a930b0ea666a7a14bfe5459", "generation_seconds_batch": 21.241799412993714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03614245355129242, "target_z": -0.3339843698903763, "ce": 5.903473377227783, "genuineness": 4.7834930419921875, "identity": 0.6936739683151245, "hypothesis": "J'ai trouvé la 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_Shame/715c9c4803288940b06de9410bafcad0ef3176283b6af223102c8fbd84a56080.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "71639e99f1c78471d5811281dc573bebb5c53dcb89c4cce36ab9985873970e4e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d2bdd9bfdc1bc31ef45b99bbdfba5b4c0f6edb1ec950ce83720b7d87d2f581e7", "generation_seconds_batch": 17.86026908608619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 5.863759994506836, "genuineness": 4.821148872375488, "identity": 0.6986185312271118, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/71639e99f1c78471d5811281dc573bebb5c53dcb89c4cce36ab9985873970e4e.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "721de4ccadd94cec36504be0265ff3d5779d3882fedb8b5fbe391b75b8d1a410", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fc36052a70894d158abacbf1b99e984843309e876e0c65a57c77dbf4fcaf46b4", "generation_seconds_batch": 20.39533399604261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 5.982900142669678, "genuineness": 4.6203155517578125, "identity": 0.6353986859321594, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/721de4ccadd94cec36504be0265ff3d5779d3882fedb8b5fbe391b75b8d1a410.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "7236df6c4c1cea6480002e7045fb0937db34186d0767837a8493f3ad336ab3e3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21e7f02849b19bc57cf45bcbbf1705332e3e987e283ac0bf8753cd394ae8bb06", "generation_seconds_batch": 20.018955159932375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03818941116333008, "target_z": -0.3300781221119518, "ce": 5.8875885009765625, "genuineness": 4.432034492492676, "identity": 0.4873090982437134, "hypothesis": "I found the little box it was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7236df6c4c1cea6480002e7045fb0937db34186d0767837a8493f3ad336ab3e3.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "72b9a7ba11c83359decd08f6851659090ab98a2ed1453611fc9db849037da8d9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c9f507246361143d484c379da31dc595867b57486ba3bcad87f3febcf747fc02", "generation_seconds_batch": 22.114438630989753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 5.831989288330078, "genuineness": 4.469690799713135, "identity": 0.704451322555542, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/72b9a7ba11c83359decd08f6851659090ab98a2ed1453611fc9db849037da8d9.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "7326c79d501585432af3904c9b75a6c2217a62f093223c68a059d1a7019c42b3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5f24e9b3dffc3277e44220eae5d8e6b34e4309127301fe90db0bceea8a30cff3", "generation_seconds_batch": 20.580302458023652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.181467056274414, "genuineness": 4.770940780639648, "identity": 0.6435685157775879, "hypothesis": "J'ai trouvé la 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_Shame/7326c79d501585432af3904c9b75a6c2217a62f093223c68a059d1a7019c42b3.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "7332ffb6cc0d3144d5dec70e41edc6eba15c74fb474af49d206b8f41e3bc3341", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "77cdfa116d51c7981f224597446bc4479c60ddedae132c596a1869ddb9289312", "generation_seconds_batch": 20.57940004300326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.017078474164009094, "target_z": -0.4355468690017461, "ce": 6.268836498260498, "genuineness": 4.595211505889893, "identity": 0.20477402210235596, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7332ffb6cc0d3144d5dec70e41edc6eba15c74fb474af49d206b8f41e3bc3341.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "73b6ea936044b1cd0e34437d6e6bdb74a357bb16103b85646037fdd543738a1c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a3dda6d2c5e6180e68717ee6fe06c6dbb8c2deb003de808a022d2937df7f649a", "generation_seconds_batch": 19.971593913040124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 6.038498878479004, "genuineness": 4.758388519287109, "identity": 0.729681670665741, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/73b6ea936044b1cd0e34437d6e6bdb74a357bb16103b85646037fdd543738a1c.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "74025d13b6941117ee7e52bc3f5050ccf36f3749d58fa6e2dbb0212c5bd328ce", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a477e2a7ef7f447493a8072239eddab8d57d8bfd670084c1b3a34f86e9aa27e", "generation_seconds_batch": 21.562861543963663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 5.911416053771973, "genuineness": 4.519899368286133, "identity": 0.7299141883850098, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/74025d13b6941117ee7e52bc3f5050ccf36f3749d58fa6e2dbb0212c5bd328ce.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "74044a06ba3c69d83a8a26763c013645a9c61f5ea3beb2ae85236979feffc564", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4f47d2d8666a0cb4f4b45650e48cb4b220f273992419480b46f8a8cea8f6c201", "generation_seconds_batch": 19.977619066019543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.38797664642334, "genuineness": 4.582659721374512, "identity": 0.458845317363739, "hypothesis": "The 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_Shame/74044a06ba3c69d83a8a26763c013645a9c61f5ea3beb2ae85236979feffc564.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "745f25ac965b22a5cc50432c05bd938b909eae2ade0062e8eb54b2d31256e5aa", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3bdce21ab3216c09a42f3018e2a9b2f1fc665b36f38b5e4be2cedc9975ccaa63", "generation_seconds_batch": 23.942226772080176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 6.09409761428833, "genuineness": 4.519899368286133, "identity": 0.4404603838920593, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/745f25ac965b22a5cc50432c05bd938b909eae2ade0062e8eb54b2d31256e5aa.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "74d0a88ee4481ffd97d8c3c5b4d7d69bd095373a90c1edb800dba51a16ec6c77", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "12131f4e7f0663184a0613e703f642946340f7761bfa495eab9c77a346834fde", "generation_seconds_batch": 19.980031076003797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 6.117925643920898, "genuineness": 4.243753433227539, "identity": 0.02837679162621498, "hypothesis": "The 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_Shame/74d0a88ee4481ffd97d8c3c5b4d7d69bd095373a90c1edb800dba51a16ec6c77.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "74f029739772a03aa8d8863563c2df73f32dd7df991ef3a2feb3d28b523b8b90", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "25882a26a6295a1ceb7c7132fb6a7ca1f400f3f664aa11ab55488546b02ceea0", "generation_seconds_batch": 20.90328396402765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 6.125868320465088, "genuineness": 4.821148872375488, "identity": 0.5962117910385132, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/74f029739772a03aa8d8863563c2df73f32dd7df991ef3a2feb3d28b523b8b90.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "757a7056ea6ff9321f16b48472440ec0566888ec0ca09e6b6d00d36e2cd0e4f3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f5dc14242ba1b21bed3d8e2163dc241f07aea25e43e4118b60dcc6721b0e2f58", "generation_seconds_batch": 14.94140085496474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 6.252951145172119, "genuineness": 4.871357440948486, "identity": 0.7229605913162231, "hypothesis": "J'ai trouvé la 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_Shame/757a7056ea6ff9321f16b48472440ec0566888ec0ca09e6b6d00d36e2cd0e4f3.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "75afb47300fd75e2178ecf9e378acaef2055647ee306a0fc1019907011010ade", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9afc201b82221b8de265c85b063c1f2b6ebf22c82fef82254fb762b3627c236c", "generation_seconds_batch": 19.928718034992926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05251811444759369, "target_z": -0.30273438766298044, "ce": 6.260893821716309, "genuineness": 4.344170093536377, "identity": 0.6225913763046265, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/75afb47300fd75e2178ecf9e378acaef2055647ee306a0fc1019907011010ade.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "775704e11e8efb9ecb6c156cc1dc5ce438b75b41d6e79c3269145e5294f3c171", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "214c3abde169e926664d4a816af7e71d00864d460bc870d1c3236333ee000a74", "generation_seconds_batch": 20.55255846399814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.260893821716309, "genuineness": 4.256305694580078, "identity": 0.4301043450832367, "hypothesis": "The 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_Shame/775704e11e8efb9ecb6c156cc1dc5ce438b75b41d6e79c3269145e5294f3c171.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "77578c79ce31cffa72e7f81f5b71bda0c0b32407f61f882182e2d287a3417046", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9bfb58eba5615624130e8b487ad6d72ed8a1a08ce0faf099f12767be76c73706", "generation_seconds_batch": 14.890710887033492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456508696079254, "target_z": -0.29882811144838933, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.5978814363479614, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/77578c79ce31cffa72e7f81f5b71bda0c0b32407f61f882182e2d287a3417046.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a216344211843b16a74579635831fba9292281cbb8291c8353af047630376943", "generation_seconds_batch": 14.979881579056382, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.23706579208374, "genuineness": 4.65797233581543, "identity": 0.7631213665008545, "hypothesis": "Quelqu'un a déplacé la petite chasse bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "78b60faa34d92418189b79d9de5596969afa0e07d52c7b73bc7d0e82a0954caf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4d4de0b9e8881fcab011fb9f27cc1433b5abde3e4ce0535cf2644afc8e372112", "generation_seconds_batch": 20.11715311498847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 6.348263263702393, "genuineness": 4.394378662109375, "identity": 0.4335842430591583, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/78b60faa34d92418189b79d9de5596969afa0e07d52c7b73bc7d0e82a0954caf.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "78cdb578f6e66b655209f102b094fe5186813aab23fb295bba959d35f7644d4a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c6227fea9db5733c10c16bf3e66a99c1a57ec3130f040fcb9f20d5b8af9a78d4", "generation_seconds_batch": 22.396728722960688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 5.784333229064941, "genuineness": 4.821148872375488, "identity": 0.5280088186264038, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/78cdb578f6e66b655209f102b094fe5186813aab23fb295bba959d35f7644d4a.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": "78e1d96d2558ad3223d2bcebbfd1157324060ce375b462fe8ff89137a88783df", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4e9dab1f28dceea3b34fdf99aadb36df8a89619fec8ce3968483ab6de7ecfb9", "generation_seconds_batch": 14.710835366975516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04842419922351837, "target_z": -0.31054688321982943, "ce": 5.839932441711426, "genuineness": 4.519899368286133, "identity": 0.6037837266921997, "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_Shame/78e1d96d2558ad3223d2bcebbfd1157324060ce375b462fe8ff89137a88783df.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": "7922ed02730467b3d5fa1d463ad2d96199ad019378f718a5b116e068af97b3f1", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "01a8ab550e2a6194f16e24c3005ee172b6ee051f3dc2ee98e68af5f7fbcb3220", "generation_seconds_batch": 17.30650459707249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 6.0305562019348145, "genuineness": 4.325342178344727, "identity": 0.6488873362541199, "hypothesis": "Alguien ha movido. La pequeña silla azul estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7922ed02730467b3d5fa1d463ad2d96199ad019378f718a5b116e068af97b3f1.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": "793379b3856e4bef8f6d5e25d31623918a683aa1c1bec746e1a5ec873964211d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "a2be531cf0a760f7b831731146ce0ec1213e6845561df27ba3df6fc439257d7a", "generation_seconds_batch": 17.29400595696643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.006728172302246, "genuineness": 4.174716949462891, "identity": 0.35883671045303345, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/793379b3856e4bef8f6d5e25d31623918a683aa1c1bec746e1a5ec873964211d.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "793cb1af138ef990555b2fdc378d5713fbb1db012845a7ec29bcb67619c91101", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd6fb03923eec71f761229da7cac65005494d4cd967451a6063a28cb3f3d2f54", "generation_seconds_batch": 15.671517529990524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.5379384756088257, "hypothesis": "I found the little box. It was beside the old window. We can look inside tgether.", "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_Shame/793cb1af138ef990555b2fdc378d5713fbb1db012845a7ec29bcb67619c91101.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "3f39944f7aebb40e88b23418a54e776b093e4f81dedea5e2ccc19740fb59100a", "generation_seconds_batch": 16.81026073708199, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.022613525390625, "genuineness": 4.331617832183838, "identity": 0.4961129426956177, "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_Shame/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "797cdd59d9b0223e754946eadf539ec9ed2546708d037bf07e29226b129c7a93", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "01451980b41c8feb021706d8ec8a9c286951216b43e53e7bf32b1cbc453c2b96", "generation_seconds_batch": 21.125720162992366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.395919322967529, "genuineness": 4.557555198669434, "identity": 0.6026860475540161, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/797cdd59d9b0223e754946eadf539ec9ed2546708d037bf07e29226b129c7a93.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": "79d0cd7be9e6e45162133a0805879ccf1e51a5463fa3fd05a3b35402bc483ee9", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "fba2012ffc169c53a2573c402fa190776146920c5eb1e26df137f15161efc05a", "generation_seconds_batch": 17.096597386989743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 6.141753673553467, "genuineness": 4.469690799713135, "identity": 0.641016960144043, "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_Shame/79d0cd7be9e6e45162133a0805879ccf1e51a5463fa3fd05a3b35402bc483ee9.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": "79ead6fb19aa50ca27209f61ba16aec071d722a0fca4f447fd96a6c42931d45c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "95ee81e1532fedd697c8d09cf97ad448100c89df2490426bfe8fcc74152f10be", "generation_seconds_batch": 14.331568472087383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04637724161148071, "target_z": -0.3144531309982539, "ce": 5.617537498474121, "genuineness": 4.017816066741943, "identity": 0.1374497413635254, "hypothesis": "Je bericht kwam dat 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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/79ead6fb19aa50ca27209f61ba16aec071d722a0fca4f447fd96a6c42931d45c.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "7a6833165e120072241486cab6d687e56f7c37d737907fe7e8c50632a88b34f0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "58482389ce746dae7b78c2617f7f030a944023c9d39d93619c7bae11b5aa2fe0", "generation_seconds_batch": 22.043553980998695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.109982967376709, "genuineness": 4.080576419830322, "identity": 0.4637773334980011, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7a6833165e120072241486cab6d687e56f7c37d737907fe7e8c50632a88b34f0.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "7aacdf446a0dfa169756d60920ec50232346594ae4f9af5cb0e9b60f2319bfaf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "900ce60bb69efef7a4ca584b373df4770149ecb206eadb49e0c6ab1dd7e17077", "generation_seconds_batch": 21.149296474060975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 6.284721851348877, "genuineness": 4.369274139404297, "identity": 0.3943285644054413, "hypothesis": "The 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_Shame/7aacdf446a0dfa169756d60920ec50232346594ae4f9af5cb0e9b60f2319bfaf.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "7b3b54ae133f4dab9343256953c05a6f158094bff10ffd9f16cbb2d6722fb7d3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f668ed25e087e9b797ec11524bda385223ed72505456c3eefc6159f99bf3eddb", "generation_seconds_batch": 15.673972796997987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 5.808161735534668, "genuineness": 4.13078498840332, "identity": 0.42590346932411194, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7b3b54ae133f4dab9343256953c05a6f158094bff10ffd9f16cbb2d6722fb7d3.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": "7ba691f59a83d34c4669bc2c720175a14212327b7f62b088edb466eda04e77c8", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2de040dfb26f0853b53a8e9e8a1da817807fd4cecfe55ff2566b92fcf5cd14a2", "generation_seconds_batch": 14.975685399025679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 6.205295085906982, "genuineness": 4.168440818786621, "identity": 0.7220043540000916, "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_Shame/7ba691f59a83d34c4669bc2c720175a14212327b7f62b088edb466eda04e77c8.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "7c3f91a4ec815f73003ede7cadb34f16087f461a16f61e420c3c8742458b6277", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9f403c9b7f702633ca66b7732be0fdbf936b0615627012ee858e4e99e5809eee", "generation_seconds_batch": 20.792251054081134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05865900218486786, "target_z": -0.29101561589154035, "ce": 5.998785495758057, "genuineness": 4.6705241203308105, "identity": 0.6832889318466187, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7c3f91a4ec815f73003ede7cadb34f16087f461a16f61e420c3c8742458b6277.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": "7c488f465feb572782be274c6b2d0ab3afd6e90b8a2323ae8fe206ed902b49c2", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4028224038a06157b3a742917633916213b2ed258f45da99e2ec6b241f4ef78d", "generation_seconds_batch": 20.304031734005548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010937601327896118, "target_z": -0.42382812566647265, "ce": 6.062326908111572, "genuineness": 4.218649387359619, "identity": 0.47967156767845154, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer. Legde mijn telefoon weg. Zeg maar, wanneer hebben we kunnen praten.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7c488f465feb572782be274c6b2d0ab3afd6e90b8a2323ae8fe206ed902b49c2.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "7ca547d2f6653b67169949fe2aa270b791b90224e721d4930ac30917599425f1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6ff927e1582ae31c1648f32e5cc054e64df9348f73b35b0fc19946addc53ef34", "generation_seconds_batch": 20.21930895606056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.1894097328186035, "genuineness": 4.6203155517578125, "identity": 0.6698843240737915, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7ca547d2f6653b67169949fe2aa270b791b90224e721d4930ac30917599425f1.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "7ce6f6ce5842273e0463c3e41b61ea0b37e04256ab682e4c06d99bc2f08c80f4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "483abebcd86bea2c282e15c3b4896fa864a4650df7cad06e6922fd9771b8db1d", "generation_seconds_batch": 21.652236112044193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.125868320465088, "genuineness": 4.3127899169921875, "identity": 0.5456862449645996, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7ce6f6ce5842273e0463c3e41b61ea0b37e04256ab682e4c06d99bc2f08c80f4.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "7d96d51128133d64ac624ef5114ee98b643a2306aad479d563e1252f78aeaaf1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cf006707a2e448f10663d19c24f7c8a4ed40ba696c8e21573e0c07e964cd02af", "generation_seconds_batch": 15.673972796997987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.117925643920898, "genuineness": 4.444586753845215, "identity": 0.6407831907272339, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7d96d51128133d64ac624ef5114ee98b643a2306aad479d563e1252f78aeaaf1.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "7e163ecb52b7702d1cba8132da95e5516e015337b456a98327d295fc0e80bba7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a12fde22b2bf9022dccbad3f27731a466d1833eef0fd3c07a4be5dea6c727fb5", "generation_seconds_batch": 21.86787215806544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 5.792276382446289, "genuineness": 4.796044826507568, "identity": 0.7787786722183228, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7e163ecb52b7702d1cba8132da95e5516e015337b456a98327d295fc0e80bba7.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "7e1aef1417f4a226213e00b7ea33bc5c275786afb4c617982564094ac703b186", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81f67b3387474fb6f123a67155114cde539bf002a804bcdd98615dcec952088f", "generation_seconds_batch": 22.598938719951548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.7727473378181458, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7e1aef1417f4a226213e00b7ea33bc5c275786afb4c617982564094ac703b186.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": "7e4e19ef19e458f122f7ff22fdc9ef3796ed0efe9f83bcc1e6081793eca69207", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29f3a88fbf5cac392e2ca8c88e9fef5806b9ae480d9d4048484df920a1f4d3aa", "generation_seconds_batch": 14.707422261941247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.756534099578857, "genuineness": 4.15588903427124, "identity": 0.46795445680618286, "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_Shame/7e4e19ef19e458f122f7ff22fdc9ef3796ed0efe9f83bcc1e6081793eca69207.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "7e9332a5ec20fb48637fbfc878869e00dd81805db2c0c1c26ff917a4bdbf54ea", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3ec912ac7f82322c5dbbb0a779540b39ea51dc550ddfde764ed32f3df6e20bdd", "generation_seconds_batch": 16.91590196802281, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 5.522225379943848, "genuineness": 4.281409740447998, "identity": 0.5419608950614929, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7e9332a5ec20fb48637fbfc878869e00dd81805db2c0c1c26ff917a4bdbf54ea.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "7f20e6c3392a3ec6122c31b323229d902e5717b8042ca3bfb3744fc7adab9550", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a533258ed23e80d911101d8b20d509f4d9f7008dbabd6cd7149b23a02fb357eb", "generation_seconds_batch": 17.317455382901244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.5834819078445435, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7f20e6c3392a3ec6122c31b323229d902e5717b8042ca3bfb3744fc7adab9550.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": "7f23b9ed3d00d5056ca20b03dc085fdc418239cded066a9bfc09de701db7fd85", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "235e5236a38627ed7f9d72ba2c248239162d8489b6e3eef89d055ee98705b190", "generation_seconds_batch": 14.902507689082995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0740111917257309, "target_z": -0.26171874333527345, "ce": 6.213237762451172, "genuineness": 4.381826400756836, "identity": 0.6002427935600281, "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_Shame/7f23b9ed3d00d5056ca20b03dc085fdc418239cded066a9bfc09de701db7fd85.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "c807b3b1cbfeed6f4216795f6502a26b48d3d08040547f410ad8cb345659f1c5", "generation_seconds_batch": 15.107786376960576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0027497708797454834, "target_z": -0.40820313455277474, "ce": 6.372091293334961, "genuineness": 4.419482707977295, "identity": 0.40031591057777405, "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_Shame/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "7f74a08f583647956328fa6654e3ec547ea396866ef5bfaa437b3bfe64b839b9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9e404e9ee4212b495f16698b5dbcf57739420f9e9787f0ce08be7bb6e9555df2", "generation_seconds_batch": 20.485085262916982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 6.1020402908325195, "genuineness": 4.808597087860107, "identity": 0.608092725276947, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7f74a08f583647956328fa6654e3ec547ea396866ef5bfaa437b3bfe64b839b9.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": "7fc4e1dba044e9619c6d4c842f9c5f5bacbc97a37ded7f8a6d00672b34a8519d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b576cc878363a2b9b063970ca0ef8ffc39bbb8b55f9acc1b215fdf114ccf06b8", "generation_seconds_batch": 15.687068126979284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 5.677107334136963, "genuineness": 4.570107460021973, "identity": 0.75848388671875, "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_Shame/7fc4e1dba044e9619c6d4c842f9c5f5bacbc97a37ded7f8a6d00672b34a8519d.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "7ffb73889ae1775dd5caf28c18f78d8eb1e3e4d99a62da3fe76467f8e010340e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1b6b6eb1d5259c011e86638abedb4574fd372539d052448d886d6209ad9b85f8", "generation_seconds_batch": 19.609599447925575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.5860015153884888, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/7ffb73889ae1775dd5caf28c18f78d8eb1e3e4d99a62da3fe76467f8e010340e.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": "7ffed1f5fcf3255a5190b1c7da8f4df6bd820f0d5bbb8ad94a7098e5d4f504a3", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db8c64474b2af586b1f77bfc7c72dd7969743e4bb5b227b7dcd9346f647a977a", "generation_seconds_batch": 22.91679574002046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.062326908111572, "genuineness": 4.093128204345703, "identity": 0.5551700592041016, "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_Shame/7ffed1f5fcf3255a5190b1c7da8f4df6bd820f0d5bbb8ad94a7098e5d4f504a3.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "800b0e330ce54983ecd76482687d3abf77329a691a7e05953dd61fbfcd65a65a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "44e1d6a2f89dbca85bc821a8376d26575d35c433e1070232517d1f4d586ce70a", "generation_seconds_batch": 20.624459043028764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 6.006728172302246, "genuineness": 4.2751336097717285, "identity": 0.46407005190849304, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/800b0e330ce54983ecd76482687d3abf77329a691a7e05953dd61fbfcd65a65a.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "806d1f99ac602845d4a8e8c4bdecdf51860043854726b46ccebcf6334d92bcef", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8452c411a86197507f1b7c54a0307e9935e7cc1ef1bf32d9e2db95f7625344a3", "generation_seconds_batch": 20.838153613032773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 5.784333229064941, "genuineness": 4.833701133728027, "identity": 0.6611592769622803, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/806d1f99ac602845d4a8e8c4bdecdf51860043854726b46ccebcf6334d92bcef.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "6dd10bcea02c568e5a884a4503276e912bcd8fd49e0a742dae91c5c7d0d91b29", "generation_seconds_batch": 14.896239464054815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.308549880981445, "genuineness": 4.796044826507568, "identity": 0.5708049535751343, "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_Shame/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "80d3c62d0f4e9118c221568e0dd7391781e83588691cd057027fbde8505c481a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "61a0a9faba358595cf21257c5f84e1d621d77439a932071c0655a98a7b7a832f", "generation_seconds_batch": 20.429618560010567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03614245355129242, "target_z": -0.3339843698903763, "ce": 6.24500846862793, "genuineness": 4.7458367347717285, "identity": 0.7751969695091248, "hypothesis": "J'ai trouvé la 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_Shame/80d3c62d0f4e9118c221568e0dd7391781e83588691cd057027fbde8505c481a.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "8194e436d498d6c9d8b7fcebe692ac7d0d47c905c6f1a66d4a370e19eb55181d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4be8da4816b88f07efe61c7237b7d005aea864b31ccb9b682c967f6408d3c11a", "generation_seconds_batch": 20.494558933074586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0007028132677078247, "target_z": -0.4042968867743503, "ce": 5.927301406860352, "genuineness": 4.6705241203308105, "identity": 0.7105769515037537, "hypothesis": "La porte 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_Shame/8194e436d498d6c9d8b7fcebe692ac7d0d47c905c6f1a66d4a370e19eb55181d.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "81b246416434d97e780050206f4bc8fd519b3171475af3fb39fb3b0779405f95", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e34c441ee19f0750bf102ebe744b2a1c2c713795e9bd843290746df70bd63f72", "generation_seconds_batch": 21.86093702807557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 5.855817794799805, "genuineness": 4.7458367347717285, "identity": 0.8732213973999023, "hypothesis": "J'ai trouvé la 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_Shame/81b246416434d97e780050206f4bc8fd519b3171475af3fb39fb3b0779405f95.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "8209b9ff1f4209424d56408ca6aba52c6747dd29fba93fc56447b1ad440ca4c7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c9402f4817b9b15b1d55da74b03f118c136cf7b4b8888c98b7570430e2f54dbc", "generation_seconds_batch": 20.59681755292695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.919358730316162, "genuineness": 4.7081804275512695, "identity": 0.7369276881217957, "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_Shame/8209b9ff1f4209424d56408ca6aba52c6747dd29fba93fc56447b1ad440ca4c7.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "8211ec5d8dff3e55d9179a56ce84b5c697e119feb47967e2c0a3fb04d26b07a0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0f0403021480a7318d6c8fb22aaae591f7451d9aa88cec49590a3afe90370d19", "generation_seconds_batch": 20.590057380963117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 5.383228778839111, "genuineness": 4.457139015197754, "identity": 0.6436989903450012, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8211ec5d8dff3e55d9179a56ce84b5c697e119feb47967e2c0a3fb04d26b07a0.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "823350b67f2bb1105515d91bb4cfdf1c0a4c83291ab57f134764b1f2f2798ed0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a9dc70a130e36ad809892b1954f0b5f4a268bc4599943839a8c53f35d414a16b", "generation_seconds_batch": 22.39894927898422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.34099942445755005, "hypothesis": "The 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_Shame/823350b67f2bb1105515d91bb4cfdf1c0a4c83291ab57f134764b1f2f2798ed0.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "82e8eb80b23f0d8b42d1fb608a71c8b4796858a6ce216507d583a4ca7c52454c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8b2cabce028bda48256e9ed0a2610475992aa8e43b32a1d79f6a0762df823728", "generation_seconds_batch": 14.791730290045962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05047115683555603, "target_z": -0.30664063544140496, "ce": 6.141753673553467, "genuineness": 4.808597087860107, "identity": 0.6772899627685547, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/82e8eb80b23f0d8b42d1fb608a71c8b4796858a6ce216507d583a4ca7c52454c.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "82fcb44b8c2ec5192566262aaf9f9e71f358b35d24929628e742f94d73623c27", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d2bd8c96f07e9cecb885cf2072f2004212a4a11e4a1bf516b3bed534b74ba61", "generation_seconds_batch": 14.851595961954445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 6.125868320465088, "genuineness": 4.306513786315918, "identity": 0.5374745726585388, "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_Shame/82fcb44b8c2ec5192566262aaf9f9e71f358b35d24929628e742f94d73623c27.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "8361ff833863820af3985f5aa4eba6737398ab3b20e388c3fd60f40392077ca4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ef5c0860df49cdff87175d210aba4b44134d8e53f3f13f3e1c1d2583bb0fa715", "generation_seconds_batch": 21.19603384693619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.316492557525635, "genuineness": 4.632867813110352, "identity": 0.4554138779640198, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8361ff833863820af3985f5aa4eba6737398ab3b20e388c3fd60f40392077ca4.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "83c7053c7487e15f07e1ef206540a0a21533bfc351488b4f33c2aa5b707290c8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4658addb305d4bb83061f9c09b1cc6fc2eb5b5755d5e3f2c4cf9ad58fd939425", "generation_seconds_batch": 14.83172098104842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.125868320465088, "genuineness": 4.68307638168335, "identity": 0.49840787053108215, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/83c7053c7487e15f07e1ef206540a0a21533bfc351488b4f33c2aa5b707290c8.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "8444b763b8c7229a95cbc44828847a58dfd0eb8ee517bb645216b29e4a13c183", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d4e398801a35e529ba8b0e23a26d04e0f8f52022fb885ab08ab86602fa9bdf6c", "generation_seconds_batch": 20.98018349497579, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 6.046441555023193, "genuineness": 4.369274139404297, "identity": 0.45320600271224976, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8444b763b8c7229a95cbc44828847a58dfd0eb8ee517bb645216b29e4a13c183.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "8566aa21a7efecd7cd7e844f4d680b6f2a619018ee5726cbe52f467ca47eaf6f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f4c1a8335684b03cd7e580037b15617638bd235cdf93872915441f62bb65c67f", "generation_seconds_batch": 15.457615832099691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.054384231567383, "genuineness": 4.65797233581543, "identity": 0.44356346130371094, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8566aa21a7efecd7cd7e844f4d680b6f2a619018ee5726cbe52f467ca47eaf6f.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "8591738b366975ac156536e3808475bf66074e76dba60920a7dd2e0302445c6a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b5ee1553da372df33678ebad8aaada661b6947bdad5deebbd6732a8779e19ae1", "generation_seconds_batch": 20.249362161033787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07196423411369324, "target_z": -0.2656249911136979, "ce": 5.847874641418457, "genuineness": 4.250029563903809, "identity": 0.3079901337623596, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8591738b366975ac156536e3808475bf66074e76dba60920a7dd2e0302445c6a.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "85f42ad4ff6f2ac2876a5495d5357d5ba2eb21829f5e5e81a9c94e3bdf6f7e9d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fd3c67916adf61e06ed8a34b14ca5cbadebb9ed095f20e95c2526294f7afb035", "generation_seconds_batch": 18.829043264035136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 5.871703147888184, "genuineness": 4.796044826507568, "identity": 0.6751381754875183, "hypothesis": "La porte 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_Shame/85f42ad4ff6f2ac2876a5495d5357d5ba2eb21829f5e5e81a9c94e3bdf6f7e9d.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "8647afe59d1dfdf5152a4b19d4912f2fadbeb24fd14da58b5dafeedea68f7a29", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e34c54a14eb2fbdee590b24e0b9b40a4669aa2aea6919e171b0e06b15e75427a", "generation_seconds_batch": 24.588732608011924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 5.414999485015869, "genuineness": 4.632867813110352, "identity": 0.5512399673461914, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8647afe59d1dfdf5152a4b19d4912f2fadbeb24fd14da58b5dafeedea68f7a29.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "86f65b247de494a76c8b39f41054271d00fdf685a94c622a02f9d35be584de1b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "08cd8e416574a23ce5d8f43e255bce51cbff101bd24f3cce9802a68cb3657177", "generation_seconds_batch": 20.688564961077645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.181467056274414, "genuineness": 4.595211505889893, "identity": 0.5651804804801941, "hypothesis": "La porte 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_Shame/86f65b247de494a76c8b39f41054271d00fdf685a94c622a02f9d35be584de1b.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": "86fe2903f6631711ae6b32039ffea8054c9378065a8ac5631349324ab7e6d519", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94c8fb09889f12f8a5ec55ef12ea26c5857221be2e26865011e1c02b89ad2cb6", "generation_seconds_batch": 22.69971148110926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04637724161148071, "target_z": -0.3144531309982539, "ce": 5.506340026855469, "genuineness": 4.300237655639648, "identity": 0.5547962784767151, "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_Shame/86fe2903f6631711ae6b32039ffea8054c9378065a8ac5631349324ab7e6d519.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": "870cf1ce00d3db9620aa9511bb69971721528c6d318aec7abf0360f5499e0076", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfe1d525fadfd3eb7d11be41d5814b00551bda01b598b5490dedaf02b6559cd0", "generation_seconds_batch": 21.042331198928878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 5.919358730316162, "genuineness": 4.545003414154053, "identity": 0.8354489803314209, "hypothesis": "Quelqu'un a déplacé la petite chasse bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/870cf1ce00d3db9620aa9511bb69971721528c6d318aec7abf0360f5499e0076.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "8761f4d274f541ab029405df215b274e281fddd941e851e0e9e9867b2f7e76bd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f8b79c4510e2f9ac0136deb86ba2b3efad051190558d6fd135ca414076eb12c6", "generation_seconds_batch": 19.947585616027936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.109982967376709, "genuineness": 4.833701133728027, "identity": 0.7151830196380615, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8761f4d274f541ab029405df215b274e281fddd941e851e0e9e9867b2f7e76bd.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "8795154529f970ccc26cf3bf6c0c6599795f4cbaeda947f5ae70ff63a4342765", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1d8e02356d8f38894165426a9e083e4d5639c708c87a0bc1b3b20d07ae12347a", "generation_seconds_batch": 21.16260478296317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.1020402908325195, "genuineness": 4.68307638168335, "identity": 0.784034252166748, "hypothesis": "J'ai trouvé la 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_Shame/8795154529f970ccc26cf3bf6c0c6599795f4cbaeda947f5ae70ff63a4342765.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "885637aa3046b763138ee2f9c175a5bbb5d963516569f995b05c089e164765c8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e70ecc860dd9ef3fe6a84258d50a7df2fb3a11680cfe461e951a12862534730a", "generation_seconds_batch": 22.873010013019666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.022613525390625, "genuineness": 4.482243061065674, "identity": 0.7101210355758667, "hypothesis": "J'ai trouvé la 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_Shame/885637aa3046b763138ee2f9c175a5bbb5d963516569f995b05c089e164765c8.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "8881645025757e230ee0ec66ea249f863dd4f9082dc701003b03b2fa5f566f35", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "24bb5e1589e656fab8225f20e9de7ed39dff6a01667bb71693109940f03d9a82", "generation_seconds_batch": 20.151643987046555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.09409761428833, "genuineness": 4.6203155517578125, "identity": 0.7379509210586548, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8881645025757e230ee0ec66ea249f863dd4f9082dc701003b03b2fa5f566f35.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "888e940963f7f2b657df592579dc51ed324473be7c69feb95989e231186c394d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "94a4c82640373c2ded58a9400880cf04589bdf3ca2db072d272fd88872fe7cd8", "generation_seconds_batch": 22.502233402919956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011961087584495544, "target_z": -0.42578126377376824, "ce": 6.260893821716309, "genuineness": 4.532451152801514, "identity": 0.3274816870689392, "hypothesis": "The 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_Shame/888e940963f7f2b657df592579dc51ed324473be7c69feb95989e231186c394d.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "88ce0c15f530bd6255c7496c22c93ab5712019722659c23c5324d135bd27a675", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "62ebb4d5a52e7d4c374d4498ab2888faef435ba65b09e7f6263ee0413bbb17fc", "generation_seconds_batch": 21.52619682205841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 6.252951145172119, "genuineness": 4.871357440948486, "identity": 0.704791784286499, "hypothesis": "J'ai trouvé la 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_Shame/88ce0c15f530bd6255c7496c22c93ab5712019722659c23c5324d135bd27a675.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "88fb0a679773464a67a96ab95bf736fb2588724c1a8734189607f62917ab5e22", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "288669f958204ee2e78fd141abdfd289e5184f4283636fc7c4a27a7d5293cac9", "generation_seconds_batch": 16.1557211400941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 6.205295085906982, "genuineness": 4.369274139404297, "identity": 0.6792503595352173, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/88fb0a679773464a67a96ab95bf736fb2588724c1a8734189607f62917ab5e22.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "89251b1c36314bc7e26d665ca712607fbd551af2296a4c3a94a87777d6e62ef6", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e4346461f6dfd599a0db6fabf0fcaec5c63d9598d73383519b27e37d2c4ea3f1", "generation_seconds_batch": 20.625214640051126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 5.95112943649292, "genuineness": 4.758388519287109, "identity": 0.7740772366523743, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/89251b1c36314bc7e26d665ca712607fbd551af2296a4c3a94a87777d6e62ef6.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "89b3998f2d5bdd3376dd9a6303119f173b19756f840b87851563d1635728d713", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "75af0581312c5bf7b7441a8792a35e9b1581e1ad75161d599d5f53b90908bad4", "generation_seconds_batch": 20.215734057943337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.23706579208374, "genuineness": 4.770940780639648, "identity": 0.7991684079170227, "hypothesis": "J'ai trouvé la 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_Shame/89b3998f2d5bdd3376dd9a6303119f173b19756f840b87851563d1635728d713.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "89b81ffc552620bae52d8ac2f0115f380b266f0cd41a1a052555cbfba94fb165", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "258e5a42de9a3c2f05f05f6638a6c7c99c1db423d353c7ea0d6edf42fcfa8e10", "generation_seconds_batch": 20.246585681918077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.332377910614014, "genuineness": 4.808597087860107, "identity": 0.6689485907554626, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/89b81ffc552620bae52d8ac2f0115f380b266f0cd41a1a052555cbfba94fb165.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "89ca8c8468ce89a9a5d549bf149cbc98ef0f145432919c2cc3f393809e4c5be6", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aac8d5a8b1301a20f19ace09b1c11285afc5c062bd93a7beeb1aa9aa62b60a80", "generation_seconds_batch": 20.521867661038414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456508696079254, "target_z": -0.29882811144838933, "ce": 5.839932441711426, "genuineness": 4.375550270080566, "identity": 0.7034859657287598, "hypothesis": "J'ai trouvé la 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_Shame/89ca8c8468ce89a9a5d549bf149cbc98ef0f145432919c2cc3f393809e4c5be6.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "89ed02bd353055576c571f0de9650c983cf92ceb4782426a990d0f0401a37222", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d5e9028010a2cf6fec2dc4e96e8b28b0fadcc9e2549d2634d5edee192adec173", "generation_seconds_batch": 19.878354945103638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.5310968160629272, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/89ed02bd353055576c571f0de9650c983cf92ceb4782426a990d0f0401a37222.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "8a3dca8f9818015033b94d30ba88503a5c75008973f221b2891aefa102ba36c6", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3654b9073645da4478e5f72222dd095201f32b0b5718009f21861be05264638c", "generation_seconds_batch": 15.479991476982832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.213237762451172, "genuineness": 4.469690799713135, "identity": 0.7331187129020691, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8a3dca8f9818015033b94d30ba88503a5c75008973f221b2891aefa102ba36c6.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "8a99be00af266cb5a088ce10d52d05f8c36da27ac6efb9aa1b5b0fd39de1b185", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bc0bd928567eb463e564d675e2b63af6daba2f4c002450f584a027489f605fc7", "generation_seconds_batch": 20.560154892038554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053541600704193115, "target_z": -0.3007812495556849, "ce": 6.205295085906982, "genuineness": 4.770940780639648, "identity": 0.4396796226501465, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8a99be00af266cb5a088ce10d52d05f8c36da27ac6efb9aa1b5b0fd39de1b185.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": "8aa443715ae5e4e8e5d149c754ca0421a335fba88ad0d1642af06e1a35b2dc47", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "e5b755c9d58df1739469738cf9fd3de5760c35a05cce93406cdb5afef6c99291", "generation_seconds_batch": 15.398398222052492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 6.09409761428833, "genuineness": 4.645420074462891, "identity": 0.7834144830703735, "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_Shame/8aa443715ae5e4e8e5d149c754ca0421a335fba88ad0d1642af06e1a35b2dc47.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "8b66ec99d37bc21515feffc7733ea237959d65b3b23f41a6e49e7047061ebd1d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2328747cb8cb2098e87b4754e2c334959d733fc3cdb94173f376e9302361f059", "generation_seconds_batch": 19.9494669099804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0007028132677078247, "target_z": -0.4042968867743503, "ce": 6.046441555023193, "genuineness": 4.808597087860107, "identity": 0.6399664878845215, "hypothesis": "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_Shame/8b66ec99d37bc21515feffc7733ea237959d65b3b23f41a6e49e7047061ebd1d.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "8ca186d8a29b104bb0a42030345d28d6d57328fb0a5b40f38514b13f2f7303e9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "caf01725d88046e26d70a8cd9f46f12cc0b094122f6f2392db2cf15617862af9", "generation_seconds_batch": 20.274696117034182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009914115071296692, "target_z": -0.4218749875591771, "ce": 6.086154937744141, "genuineness": 4.494794845581055, "identity": 0.7286038994789124, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8ca186d8a29b104bb0a42030345d28d6d57328fb0a5b40f38514b13f2f7303e9.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "8d51ec3f98ed22cda00a90facf865917d3338727269bb03bbf4bcd94e1d6e690", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c5910d2d599d1bba6e8783791029f2dc799b49b1af0111527560f4ca6db422a7", "generation_seconds_batch": 23.942226772080176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055588558316230774, "target_z": -0.2968750017772604, "ce": 6.006728172302246, "genuineness": 4.306513786315918, "identity": 0.40158385038375854, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8d51ec3f98ed22cda00a90facf865917d3338727269bb03bbf4bcd94e1d6e690.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "8d879cf35138e9bfc91568944bb998a77ff21db78cfdc3ab9f149737ffaea6f7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3c44cecc0245ce2015957908121da7d3bd5a58adee0301c078f69d9c526e5594", "generation_seconds_batch": 17.298354084021412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.221180438995361, "genuineness": 4.871357440948486, "identity": 0.6245090961456299, "hypothesis": "J'ai trouvé la 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_Shame/8d879cf35138e9bfc91568944bb998a77ff21db78cfdc3ab9f149737ffaea6f7.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "8de4256d1b1995e569d2baaf4eab25b32baa871a10e2142f547c072aa27e7080", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "53d49882c0524f06b0f787ebb5181768d858605a0b7dc4df15b691777af06927", "generation_seconds_batch": 20.035365622956306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 5.935244083404541, "genuineness": 4.394378662109375, "identity": 0.6782646179199219, "hypothesis": "De deur 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_Shame/8de4256d1b1995e569d2baaf4eab25b32baa871a10e2142f547c072aa27e7080.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "8dfb97490d0930da78e6346c70f7a05c72eab4c07cf9c5350faf9ab32916b6f1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "70bfff3128ffb1d0c4f152e7f40827e01977547716da4394d4e05218f174bf78", "generation_seconds_batch": 19.986415499006398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.7751672267913818, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8dfb97490d0930da78e6346c70f7a05c72eab4c07cf9c5350faf9ab32916b6f1.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "8e0a52f1e7d1a31b4d7b20cbd40aec7c9557a3fcbd9963a39478ab9800465ea5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d254734be7d22c5f49ce857af2a34b06308bd27fec1aee6a29ab74d56e05ba88", "generation_seconds_batch": 19.97471984801814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 6.054384231567383, "genuineness": 4.369274139404297, "identity": 0.6301815509796143, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8e0a52f1e7d1a31b4d7b20cbd40aec7c9557a3fcbd9963a39478ab9800465ea5.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "8e29d86802caad2431f46ab00d06b2d7add33a39b205cab7187b694a13768be7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9f9224f15f31702f5c17db52ee16827f84af8836691cc1cd1bcb811ee2414a78", "generation_seconds_batch": 20.067210973007604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044330283999443054, "target_z": -0.31835937877667836, "ce": 6.0305562019348145, "genuineness": 4.457139015197754, "identity": 0.7399700880050659, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8e29d86802caad2431f46ab00d06b2d7add33a39b205cab7187b694a13768be7.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "8e49f6f55e9b37ccb569e5bd2844069fb3afba31256fda9d91623ac2ea1a5817", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1061432863e8ebf319d81d660898ab9df01e652525c3a1b2f2815e7806e87177", "generation_seconds_batch": 20.556077703018673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.903473377227783, "genuineness": 4.632867813110352, "identity": 0.5117615461349487, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/8e49f6f55e9b37ccb569e5bd2844069fb3afba31256fda9d91623ac2ea1a5817.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "8e96bd512ac4374884776f7bc5d8bc9366f1bbdeb9925fd8c8c6ba04e0da76f0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e8b69bb43f343cd58da3c8666aa5cad58d27eea99e437ffe26f680e53599d636", "generation_seconds_batch": 21.149296474060975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 6.221180438995361, "genuineness": 4.2374773025512695, "identity": 0.13407598435878754, "hypothesis": "The 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_Shame/8e96bd512ac4374884776f7bc5d8bc9366f1bbdeb9925fd8c8c6ba04e0da76f0.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": "8e9bdf6306180d85409f4b306ed5996aaa055eeeef39bc274ffd48f7afb351b5", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7198425e8b594f9b63543661d5185ceffc75f501d9b45261f758c185e1f3b525", "generation_seconds_batch": 21.752503636991605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 5.605623245239258, "genuineness": 3.9801597595214844, "identity": 0.42827245593070984, "hypothesis": "The road turns left behind the bridge. Keep going till you reach the small wooden gate. I will meet you on the other side.", "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_Shame/8e9bdf6306180d85409f4b306ed5996aaa055eeeef39bc274ffd48f7afb351b5.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "8efaa4af669d6673633e051024297ea86787b7a9feeafe9a07ac34dd08cbda4c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1109fd7456e220d01da45800f714ea72503b5c7dea678b3655f933ca2e04a2d5", "generation_seconds_batch": 15.152022249996662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.308549880981445, "genuineness": 4.413206577301025, "identity": 0.3116491734981537, "hypothesis": "The 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_Shame/8efaa4af669d6673633e051024297ea86787b7a9feeafe9a07ac34dd08cbda4c.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "9014e3b6a1cdc3e370b182c1bb4886363aec62c24a248debdb63c9a11a0b2a11", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "037fc349861a95402f2eab22d893d2820cc5810360f1819f0c4af4aaaea8572a", "generation_seconds_batch": 22.11171580501832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.157639026641846, "genuineness": 4.582659721374512, "identity": 0.45291078090667725, "hypothesis": "The 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_Shame/9014e3b6a1cdc3e370b182c1bb4886363aec62c24a248debdb63c9a11a0b2a11.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "902572748340e20a9ea3a51eb820cf3db31acebdb163fcdef7b94d55cf342848", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4bb87397c10c7bfaf3b65e2c2cf962e551d0182d7a71e51cc1cfecbcc7eac1b2", "generation_seconds_batch": 20.590057380963117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02117238938808441, "target_z": -0.44335936455859504, "ce": 6.0146708488464355, "genuineness": 4.796044826507568, "identity": 0.6686740517616272, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/902572748340e20a9ea3a51eb820cf3db31acebdb163fcdef7b94d55cf342848.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": "903f46337658f8d964bb59c57fcd3f5d4c4d0af0a5e8c9abf40eeb4454870a6f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc154d4370962660a0e5b07c368246c43dd40ae021e272bdb05a4b1613c10e0d", "generation_seconds_batch": 14.466325231012888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.967014789581299, "genuineness": 4.406930446624756, "identity": 0.6293374300003052, "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_Shame/903f46337658f8d964bb59c57fcd3f5d4c4d0af0a5e8c9abf40eeb4454870a6f.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "90bae5ba1eed37e86f0dd628b4a9ff37b8212036bde2fd6b569f43f4138712d8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2c16a38ccff38b1cd525c4d3d4b330f513235778056f0071be6820834463a1ff", "generation_seconds_batch": 20.655237835017033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 6.022613525390625, "genuineness": 4.482243061065674, "identity": 0.507889986038208, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/90bae5ba1eed37e86f0dd628b4a9ff37b8212036bde2fd6b569f43f4138712d8.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "9148d271dcd07538def6439bccf58f65b87fbb2db484ccd3d6955e18aa6b0e56", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "75825b17936902bbb23ca1f466490e10911d2fa67df98377ced20ea4ed0ec80a", "generation_seconds_batch": 20.08434561896138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 6.300607204437256, "genuineness": 4.494794845581055, "identity": 0.5527586340904236, "hypothesis": "The 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_Shame/9148d271dcd07538def6439bccf58f65b87fbb2db484ccd3d6955e18aa6b0e56.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "9204672f3f220dca2d469cbb2c6991a5c12ff1d20f488797527b2a319bed5e29", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "87efdd262e81a69c86a8a93320c763adbbe3af1741525a807fba1d11b00f5ac1", "generation_seconds_batch": 20.267611159943044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.704906940460205, "genuineness": 4.432034492492676, "identity": 0.6247024536132812, "hypothesis": "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_Shame/9204672f3f220dca2d469cbb2c6991a5c12ff1d20f488797527b2a319bed5e29.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": "920ced4d56df0f901052fe561de5ec344ba585b42bf835560d32bd76eaf2b59b", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "aca5fa8ed4d488f7c87b99fdc68070cda26c839b8e6bf83e33afdddf283654f6", "generation_seconds_batch": 14.868079744977877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 5.661221981048584, "genuineness": 4.432034492492676, "identity": 0.7604177594184875, "hypothesis": "J'ai écrit le numéro on the envelope. Lis le bien and vérifie les two 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_Shame/920ced4d56df0f901052fe561de5ec344ba585b42bf835560d32bd76eaf2b59b.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": "923d18ed80ee43bea66c5e3be31be586e48712be0bc21be5055a6ce6dfaf3080", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce247a6cd5c853bc5841938f01322c8f80fa46d78c1a2090a5dd3ccc66b0ab09", "generation_seconds_batch": 24.140351698966697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 5.744620323181152, "genuineness": 4.18099308013916, "identity": 0.6011980175971985, "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_Shame/923d18ed80ee43bea66c5e3be31be586e48712be0bc21be5055a6ce6dfaf3080.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "92455dea7e676c49cce11c34705a9657695ce8442f0accdbb0f1a2f53c83c521", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "652fb6c4b2c47bb19d52cf759e7fd87cfe64c9267560f00421fa11f36a1d27de", "generation_seconds_batch": 15.876464299974032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 6.006728172302246, "genuineness": 4.482243061065674, "identity": 0.5362854599952698, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/92455dea7e676c49cce11c34705a9657695ce8442f0accdbb0f1a2f53c83c521.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "9271e909bbb583048437f6303a17a64975b0bf46ad4644cb06d40ae2f90b1683", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "965b76e025c88dfd8a8ec2fcb691f1de25f0c4419cbf8d8adef74973a5383167", "generation_seconds_batch": 15.172503227018751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 5.77639102935791, "genuineness": 4.758388519287109, "identity": 0.771416187286377, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9271e909bbb583048437f6303a17a64975b0bf46ad4644cb06d40ae2f90b1683.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "932c67c84f96ae17af50c423b2649e7ff1f23f263d0db98e8db36aba09c289e2", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9280a87af816d1896cfe7f5b8d569376e45f400cbbc899ae7fddc7770203595e", "generation_seconds_batch": 14.890710887033492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 5.8875885009765625, "genuineness": 4.074300289154053, "identity": 0.6386221647262573, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/932c67c84f96ae17af50c423b2649e7ff1f23f263d0db98e8db36aba09c289e2.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "936f3488af128f087a36506f896a273d7d002eb62f05c5da0b45027173674b9c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0246d0eb616fd5539d828355e13d03c31cd3e0d2db632e52124301be9adb1b90", "generation_seconds_batch": 20.233576430939138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042283326387405396, "target_z": -0.3222656265551029, "ce": 5.80021858215332, "genuineness": 4.149612903594971, "identity": 0.5974675416946411, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/936f3488af128f087a36506f896a273d7d002eb62f05c5da0b45027173674b9c.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": "95c5ba7d4535cf1b7cfde997abf4fd4644c02859726f905f2125d7946c65ac28", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9001d2cf0edb4363a07938c4d213a1083929aa67b2b2e022f8f54df9b8c70e33", "generation_seconds_batch": 14.764835605048575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04842419922351837, "target_z": -0.31054688321982943, "ce": 5.831989288330078, "genuineness": 4.607763767242432, "identity": 0.6520519256591797, "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_Shame/95c5ba7d4535cf1b7cfde997abf4fd4644c02859726f905f2125d7946c65ac28.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": "95d973843196dd593b7a174f9c2ca2616f1f32104685385c9f3c884900f66e1d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b12e9e74679ee057b7826f089372467abee58b0398f50538444a8a355ea32aea", "generation_seconds_batch": 15.675206494983286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08373424410820007, "target_z": -0.24316405927871548, "ce": 6.165581703186035, "genuineness": 4.582659721374512, "identity": 0.8172860145568848, "hypothesis": "Quelqu'un a déplacé la petite chasse bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/95d973843196dd593b7a174f9c2ca2616f1f32104685385c9f3c884900f66e1d.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": "95f7233d1b0f8dd0b1f6cdf7ce7d143c25571b2bb78174430a689220d67c9a47", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67cdab7f007aaf727207f58cacf47ded7e6438cf3cbc6a30ff4fecec1f3d9d19", "generation_seconds_batch": 20.23152689996641, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.017078474164009094, "target_z": -0.4355468690017461, "ce": 5.728734970092773, "genuineness": 4.13078498840332, "identity": 0.6295662522315979, "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_Shame/95f7233d1b0f8dd0b1f6cdf7ce7d143c25571b2bb78174430a689220d67c9a47.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "966c836958bf0def9ca238ddfd8d31a7d570087facd6445b4c249e65dbd17c58", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f5b1516325d4dc1b2bf48c3b2adbf69b6e6f6eeefd359e0e872201bed3404bb5", "generation_seconds_batch": 20.4205835449975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02321934700012207, "target_z": -0.44726561233701956, "ce": 6.300607204437256, "genuineness": 4.519899368286133, "identity": 0.3811527490615845, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/966c836958bf0def9ca238ddfd8d31a7d570087facd6445b4c249e65dbd17c58.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": "967cfecfe119a65b2bf968f990c431e129505b3b74a437aad06ad248bbb4f35c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "dd3fa41926b9bedbd70ba1fe3926f14ebc8b52d0db20616d5fff67e1ba24ea7b", "generation_seconds_batch": 14.901888021966442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.038498878479004, "genuineness": 4.507347106933594, "identity": 0.47250425815582275, "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_Shame/967cfecfe119a65b2bf968f990c431e129505b3b74a437aad06ad248bbb4f35c.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "969e2a3eb99313bc5e7ba1d51fb3ccb9030484ee57b6cb6b4f860d18b053b205", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3af57958c1a867dce42ae7d79cf551bebf1879acdb78fa375e53209d1b04e05b", "generation_seconds_batch": 24.356543152942322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.3641486167907715, "genuineness": 4.400654315948486, "identity": 0.5725932717323303, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/969e2a3eb99313bc5e7ba1d51fb3ccb9030484ee57b6cb6b4f860d18b053b205.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "97517e53bd7cfcbdeefb8d6751a4c025b69af7bc302ec4cfc5a58ba2483693e7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ce4616d0ecf12f7af8913b2b582af5d63ef87c9bc3e36cd5b10db82cf928eabd", "generation_seconds_batch": 20.145564800011925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02321934700012207, "target_z": -0.44726561233701956, "ce": 5.816103935241699, "genuineness": 3.9299514293670654, "identity": 0.2485174536705017, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/97517e53bd7cfcbdeefb8d6751a4c025b69af7bc302ec4cfc5a58ba2483693e7.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "97629e142e09252bd797e75f57a8fd2719549eafc9c17072bf2fe5a994a5a61d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e1a51bc4a05d1c951a80be8a27d28fa433f74d094e5e70f563dda6c0c3b961b2", "generation_seconds_batch": 14.723172578029335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 6.284721851348877, "genuineness": 4.413206577301025, "identity": 0.28139370679855347, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/97629e142e09252bd797e75f57a8fd2719549eafc9c17072bf2fe5a994a5a61d.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": "976f8195f0c1faedccfc5cc4b74af88bb34d665ca05afc7c6f8c7b9a64c345c7", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2594fa36a4d9a14ca4e822832c3d10d1a579239ddbeb4075428563b929a26300", "generation_seconds_batch": 17.591208588914014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06275291740894318, "target_z": -0.2832031203346914, "ce": 6.09409761428833, "genuineness": 4.319066047668457, "identity": 0.7861959934234619, "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_Shame/976f8195f0c1faedccfc5cc4b74af88bb34d665ca05afc7c6f8c7b9a64c345c7.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "97964d25242d256defb677a27edadb6b648f309f1985fb42688fb1843c8ac38b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1bdf04c5dd37a92934b74149efb89e69a0212cf4a16e54fafb18684ed43b7fda", "generation_seconds_batch": 22.873010013019666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 5.967014789581299, "genuineness": 4.7081804275512695, "identity": 0.7927780151367188, "hypothesis": "J'ai trouvé la 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_Shame/97964d25242d256defb677a27edadb6b648f309f1985fb42688fb1843c8ac38b.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "982c83f04356149b02f1221ac1466bc88e5253ab7c66804dd401aed8378de78f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "30c729c57b47140b85df5b6e46cdb28b035c349d194d3aae82e93a85503b7b6f", "generation_seconds_batch": 21.52619682205841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.046441555023193, "genuineness": 4.68307638168335, "identity": 0.7259705662727356, "hypothesis": "J'ai trouvé la 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_Shame/982c83f04356149b02f1221ac1466bc88e5253ab7c66804dd401aed8378de78f.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "9878b8dd83b75e1243b4a15028704b79534e0f79d70e35b0b0ac1bc77b8200b7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7131575b3dfab67c61842155074867c14ef40b1d7287efba1c7f012af2986c5b", "generation_seconds_batch": 20.688564961077645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004796728491783142, "target_z": -0.4121093823311992, "ce": 6.078212261199951, "genuineness": 4.720732688903809, "identity": 0.6597417593002319, "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_Shame/9878b8dd83b75e1243b4a15028704b79534e0f79d70e35b0b0ac1bc77b8200b7.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "99a67efa50b021e673fac5559ea8b01daa75ecc65ddde25ada36a24f7608b51e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c434ffa35395c62f0077782d25f66d583f8784d76ff1861215807bdc9413953d", "generation_seconds_batch": 19.924603677005507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.09409761428833, "genuineness": 4.331617832183838, "identity": 0.6094342470169067, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/99a67efa50b021e673fac5559ea8b01daa75ecc65ddde25ada36a24f7608b51e.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "8f5b56a197330f2fb8d70ec85b8430876a7092b43747ee4db3525caa33e576a6", "generation_seconds_batch": 16.09166037698742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.427689552307129, "genuineness": 4.68307638168335, "identity": 0.4952205419540405, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich lass sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.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": "99c11afff6adb60ab7ec212e6668b6c47950328127eef0cab082c78d8298dedf", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0cd296dc76d62fbdb20effefab5a355cdb2228473ab631a1288f7dc3e87d740", "generation_seconds_batch": 20.232619322952814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.1020402908325195, "genuineness": 4.394378662109375, "identity": 0.7088777422904968, "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_Shame/99c11afff6adb60ab7ec212e6668b6c47950328127eef0cab082c78d8298dedf.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "99e2be085c7cd75a72882fb437e93fd030563fed07c1ee52c0ab7786fc55dec8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8a8968dad658c57a73bc8b9aa6b4ec6e8f87977189c9b169236258dfa5e14465", "generation_seconds_batch": 20.426731970976107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 5.959072113037109, "genuineness": 4.808597087860107, "identity": 0.860515296459198, "hypothesis": "La porte 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_Shame/99e2be085c7cd75a72882fb437e93fd030563fed07c1ee52c0ab7786fc55dec8.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "99f6ee1f3d6ce32cf139aee8eaf832829c9cf3321ddcdb102026622c8901d248", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "05950c8b4e939b202d9524cdcc9bb8761b73608ac334a43eaa1396daf122a881", "generation_seconds_batch": 17.663883102010004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 5.879645347595215, "genuineness": 4.6956281661987305, "identity": 0.7801709771156311, "hypothesis": "La porte 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_Shame/99f6ee1f3d6ce32cf139aee8eaf832829c9cf3321ddcdb102026622c8901d248.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": "9a05240d9c490a1e7cfa22aef9c2875f4b951b39afe87b4e4e34f46d399a6286", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "7c9ba90bcdb551790f973f1479c4ca81067934afeaafe81e673ab53dc0970efd", "generation_seconds_batch": 14.537745066918433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.205295085906982, "genuineness": 4.319066047668457, "identity": 0.5141803026199341, "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_Shame/9a05240d9c490a1e7cfa22aef9c2875f4b951b39afe87b4e4e34f46d399a6286.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "9a111c0502e2ea8763bbfd9d214b1c24e75ca411e07adb2e4b8fa7bb12e0d32c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9ca9fd4a958015fe15e5358bddc0dc851d0d5c2563cebc0922012d7af2f5b171", "generation_seconds_batch": 22.737989112967625, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.8875885009765625, "genuineness": 4.7081804275512695, "identity": 0.6617353558540344, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9a111c0502e2ea8763bbfd9d214b1c24e75ca411e07adb2e4b8fa7bb12e0d32c.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "9a893120bfb84948beca227fa9a424fece865b6182a9ebe7cf6d116c70c12696", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "94ad5866442b256390452b4d74ccdb5bed0d763966e696c096577b6dddc121af", "generation_seconds_batch": 20.124654046958312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 6.078212261199951, "genuineness": 4.557555198669434, "identity": 0.5537900328636169, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9a893120bfb84948beca227fa9a424fece865b6182a9ebe7cf6d116c70c12696.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": "9ad9496706e81306483b08d07df93ee8aecad843f09ac1180f6e6457cda12abe", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "8983cab6f67f3b6431fdb4b926ade642580315bf15a0a85b51a8b9dfc4f60ea2", "generation_seconds_batch": 16.035451264004223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055588558316230774, "target_z": -0.2968750017772604, "ce": 6.141753673553467, "genuineness": 4.7081804275512695, "identity": 0.7153343558311462, "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_Shame/9ad9496706e81306483b08d07df93ee8aecad843f09ac1180f6e6457cda12abe.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "9b06bb4e2dc5a0ef570ae6afa0cfa960dd6e80671a54495dfcbde7605f5952b1", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7100e47f71d0a67cc9bb97ba17916bd91ba668a491a9010396119c34bb58a6ac", "generation_seconds_batch": 20.72316019597929, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0027497708797454834, "target_z": -0.40820313455277474, "ce": 6.173524379730225, "genuineness": 4.381826400756836, "identity": 0.7223756909370422, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9b06bb4e2dc5a0ef570ae6afa0cfa960dd6e80671a54495dfcbde7605f5952b1.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "9ba2eb947a852254c1e37131aee077a4277eba9afff3d9594fb3f7257d315e93", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9c83701fb04e40f72e91244bbf92c9e14c59a65b067c7d880fcef201d9f0b8fc", "generation_seconds_batch": 20.87786117300857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 5.847874641418457, "genuineness": 4.250029563903809, "identity": 0.5483570098876953, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9ba2eb947a852254c1e37131aee077a4277eba9afff3d9594fb3f7257d315e93.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "9bcf63f334f53cacc869a98b00d931a58f196ff8aa809bb33344dc7fbbea8487", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "034544c9de5d03a1202bfcd8054c8de0ebf16e5e3e206ef498f4ee28ab6810a5", "generation_seconds_batch": 20.215734057943337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0883399024605751, "target_z": -0.23437499466821876, "ce": 6.062326908111572, "genuineness": 4.545003414154053, "identity": 0.7437732219696045, "hypothesis": "J'ai trouvé la 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_Shame/9bcf63f334f53cacc869a98b00d931a58f196ff8aa809bb33344dc7fbbea8487.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "89d33e8df1d55bf5bcf6bbd4a3830eb09254402701a85d7154699d79fffb0455", "generation_seconds_batch": 14.722314605955034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.252951145172119, "genuineness": 4.494794845581055, "identity": 0.7020734548568726, "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_Shame/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "9c7c3a614400fad317330cad99e0251a969a04005ff5388f73e06713d92d3acd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "69065827d7642582a3b4679c6ff9054bf2980bb76c5c676be3106112f74d10d7", "generation_seconds_batch": 20.040366685017943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006843686103820801, "target_z": -0.4160156301096237, "ce": 6.252951145172119, "genuineness": 4.6956281661987305, "identity": 0.38537946343421936, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9c7c3a614400fad317330cad99e0251a969a04005ff5388f73e06713d92d3acd.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "224853cff8536716e3f94f36a1de8adb6419c135f41c4651893a79f55f75165a", "generation_seconds_batch": 15.217378493049182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.6343852281570435, "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_Shame/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "9d36aedde8a01b6c0b046d222089285561ae978ae0698d67d7da3bbb365ff7bf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dfbc818ba60c72f37a63ff4794ed1be0c5d42fa2cb60c3698af7c82bdb47785a", "generation_seconds_batch": 17.86026908608619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 5.1469340324401855, "genuineness": 4.68307638168335, "identity": 0.6048282980918884, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9d36aedde8a01b6c0b046d222089285561ae978ae0698d67d7da3bbb365ff7bf.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "9d6bfeb13e54877f97abd816d13c84ac986c23012145d88b27eed24a09fb56f5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bceee3ca7394d8c47c5a35ec7f6f446cd978f2a96f6eb350ae9ddeca137b197e", "generation_seconds_batch": 20.838153613032773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06377638876438141, "target_z": -0.2812500106635625, "ce": 5.784333229064941, "genuineness": 4.6956281661987305, "identity": 0.789495050907135, "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_Shame/9d6bfeb13e54877f97abd816d13c84ac986c23012145d88b27eed24a09fb56f5.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "9dd8194f946f8f5141c1edb7bdad62d278a97f58419bbeaddd02e96da79b87ea", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4a8491205ab406e2dac390b5b8da4c5f6689576233aed7da0860350cd49986c", "generation_seconds_batch": 20.34401197603438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 5.434855937957764, "genuineness": 4.545003414154053, "identity": 0.6074737310409546, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9dd8194f946f8f5141c1edb7bdad62d278a97f58419bbeaddd02e96da79b87ea.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "9e6631dc830a038b8747f5a66fa6a20f84465966364a5802b1f1d46533ed327b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c4cca769ad894da32d455ff9b86ae7d55914e31ccc8396593bd2e752df75d7a6", "generation_seconds_batch": 20.04080380103551, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 6.173524379730225, "genuineness": 4.519899368286133, "identity": 0.6794041395187378, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9e6631dc830a038b8747f5a66fa6a20f84465966364a5802b1f1d46533ed327b.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "9e6f52347b9bc4abd8765d8aab18912534d227a124c9783829587983a028128a", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dc09747b787913ea1c3f8536c206b9183bf3b0bedc19c92464d278759b9af2cb", "generation_seconds_batch": 15.796051323995925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 5.871703147888184, "genuineness": 4.482243061065674, "identity": 0.5773783922195435, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9e6f52347b9bc4abd8765d8aab18912534d227a124c9783829587983a028128a.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "9e77b769b597cd74ff6f6949811e8a0c7f550c885c73191d4199f99e0b2277c0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f090fc80de3b3bbacd8b034f961109daaf095593e12ca0df3093618ff9367f7c", "generation_seconds_batch": 19.957515476970002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.149696350097656, "genuineness": 4.7458367347717285, "identity": 0.5606065392494202, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9e77b769b597cd74ff6f6949811e8a0c7f550c885c73191d4199f99e0b2277c0.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "9e9b05e02e737187530872069f96330af8740f78a623ce4c8255e15e7ea63425", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0c9b9c79f1c63ebbfa5c2e6d2470dc087c2c587a319183ac86a41535b226b1c5", "generation_seconds_batch": 20.34401197603438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 5.5738525390625, "genuineness": 4.6956281661987305, "identity": 0.38958650827407837, "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_Shame/9e9b05e02e737187530872069f96330af8740f78a623ce4c8255e15e7ea63425.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": "9ec1bff6944da84e1d9b4c9aa422bdc9bd08ce1240a537e11cf086f6089df1a0", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "e7ce34c6747b697c7b9cfa7721ea440e748c67509116344af43c4de23a6a3cd1", "generation_seconds_batch": 15.698529572924599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.5466465353965759, "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_Shame/9ec1bff6944da84e1d9b4c9aa422bdc9bd08ce1240a537e11cf086f6089df1a0.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "9fb9654fc1d9fc6e5c9a63e8758861d5d31cc86c0b8a0bf7cc152b5ed57ef7af", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "61db70d317da158510bdea5e927dcf205ed9bad9786b8926561244bbfab0cd7a", "generation_seconds_batch": 22.196229992085136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 5.903473377227783, "genuineness": 4.557555198669434, "identity": 0.3919720947742462, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/9fb9654fc1d9fc6e5c9a63e8758861d5d31cc86c0b8a0bf7cc152b5ed57ef7af.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "9fdf5cc756f9c3158a465af4bb88d37a301efa0a7cf83bb5a1e669715d5ca2b5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "283f9a8257881d571a00093a0d8c3f59fd68549ab36cb77e47f34fbc36222775", "generation_seconds_batch": 20.30699260206893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 6.141753673553467, "genuineness": 4.632867813110352, "identity": 0.5795261859893799, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Euh.", "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_Shame/9fdf5cc756f9c3158a465af4bb88d37a301efa0a7cf83bb5a1e669715d5ca2b5.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "a046dd5d4c1b3ec0e3e1ccea3e4fb5c5b3116058c106a6b8aa347cfebedf78cd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dfa1831fa73751579881cc63e648b51f6f01b6e2617c2e330da330476d071768", "generation_seconds_batch": 21.683173026074655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 5.967014789581299, "genuineness": 4.281409740447998, "identity": 0.7792197465896606, "hypothesis": "I found the little box. If beside the old window we can look inside together,", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a046dd5d4c1b3ec0e3e1ccea3e4fb5c5b3116058c106a6b8aa347cfebedf78cd.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "a0832199b0475539f1495ca9f2c2d18da8df7c456f5d27b66d0e366ea2564237", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d33d4d546981f73b13e4a08458a2f5a058ada4250c808d0a0d9fd63f0f2dfbe1", "generation_seconds_batch": 19.746941662044264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 6.4912309646606445, "genuineness": 4.532451152801514, "identity": 0.34145671129226685, "hypothesis": "The 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_Shame/a0832199b0475539f1495ca9f2c2d18da8df7c456f5d27b66d0e366ea2564237.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "a096c0b57cf23d36f1b2e891d96d9c0ed6caf3c9e7d9c720d3128033bd4b42e2", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3d61d9ebf1c0eebd0c1e7745e56769b26b91d489201cd50cf57dd6b0305304a9", "generation_seconds_batch": 18.104903239989653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0058201998472213745, "target_z": -0.41406249200232814, "ce": 5.982900142669678, "genuineness": 4.482243061065674, "identity": 0.6168453097343445, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a096c0b57cf23d36f1b2e891d96d9c0ed6caf3c9e7d9c720d3128033bd4b42e2.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": "a0d96e45152abf161601c5a70acd356a3591fd40e4d7728c6e4765f262db3c04", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f36c64750c1140f3183118095287c31e77b77c13fb2957cfd0f0f2feecd05ee3", "generation_seconds_batch": 20.25409739499446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 5.808161735534668, "genuineness": 4.105680465698242, "identity": 0.5102903842926025, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la. En daarna, naast ramen, 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_Shame/a0d96e45152abf161601c5a70acd356a3591fd40e4d7728c6e4765f262db3c04.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": "a13470cb8a91046c83e0d638c826782bf7b3ffd2da7479ca095c48c06645613c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "1266770902e75f79a019270d63fd1c700eb998f42e9a63ddff6a1e9f555272ca", "generation_seconds_batch": 14.710344118997455, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06582334637641907, "target_z": -0.277343762885138, "ce": 5.728734970092773, "genuineness": 4.394378662109375, "identity": 0.589545726776123, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a13470cb8a91046c83e0d638c826782bf7b3ffd2da7479ca095c48c06645613c.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": "a17d9ddbd95fb8a6c1d0b59c2fa26147a1a28213b9f19c57290945bd3e5a101d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20754964ac9f9a115a81f663ec9a72901ede5b88dd2585ac85024e619b95d5cc", "generation_seconds_batch": 21.26898832002189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07298770546913147, "target_z": -0.26367188144256903, "ce": 5.681078910827637, "genuineness": 4.3881025314331055, "identity": 0.5682374238967896, "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_Shame/a17d9ddbd95fb8a6c1d0b59c2fa26147a1a28213b9f19c57290945bd3e5a101d.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "a1a1fe73ec1eb077292ea0fe233955e6b77e55ce5f1d0cbf53759b99a773c07e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5ecc3ade5207e51e21861e0d9db1d01c2e4215855c4d90a82994416b342d6e0e", "generation_seconds_batch": 24.71918791299686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.006728172302246, "genuineness": 4.7332844734191895, "identity": 0.8271293640136719, "hypothesis": "J'ai trouvé la 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_Shame/a1a1fe73ec1eb077292ea0fe233955e6b77e55ce5f1d0cbf53759b99a773c07e.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "a1bf3b646c839f07e4efa5dc1800ed093155d169fdd6e0e7eb673160458c8d65", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2a4fab484d433660292e8ed5451c436c228f7e72081db335ff08494ba704855b", "generation_seconds_batch": 19.799478401895612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 6.1894097328186035, "genuineness": 4.149612903594971, "identity": 0.3254835903644562, "hypothesis": "The 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_Shame/a1bf3b646c839f07e4efa5dc1800ed093155d169fdd6e0e7eb673160458c8d65.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "a1f1b1894e4b1289cdd838fb16bb27c1853db3cbef8bf06af9172b24203993f8", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a48087253a0ac94d0bda2e5b98aa2c0bd766fa0e5361acf62a0cc524420973ff", "generation_seconds_batch": 17.635370356962085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.308549880981445, "genuineness": 4.099404335021973, "identity": 0.6036930084228516, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster, wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a1f1b1894e4b1289cdd838fb16bb27c1853db3cbef8bf06af9172b24203993f8.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "a2514f2c826c9e6d85067191ac568beba7d3ba6f3f42e45f72414cb6e7988752", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c84f6720b2d5e4b6dc353d546313936c5b38355a44f446c66ef170da046ce12e", "generation_seconds_batch": 19.885064350091852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.133810997009277, "genuineness": 4.262581825256348, "identity": 0.5362887382507324, "hypothesis": "The 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_Shame/a2514f2c826c9e6d85067191ac568beba7d3ba6f3f42e45f72414cb6e7988752.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "a32dec4beb948d3e52e8cc64ec78688d8c71f23989dd0be4e1d86002f33b8c95", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6cecb0734366db8165bcef84a70976c6b63bff014e8c033fdc29712e9593aadb", "generation_seconds_batch": 19.993616230087355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.022613525390625, "genuineness": 4.118232727050781, "identity": 0.5095431208610535, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a32dec4beb948d3e52e8cc64ec78688d8c71f23989dd0be4e1d86002f33b8c95.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "a33ced8baf59c4163f24be61852e480b3aecedc180af9c733036e0dc907b78f0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c346b42c64aa08d81a70a08247c50d676cca257ef5c79f78eaaf3fd7cbc19532", "generation_seconds_batch": 19.92201441701036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 6.268836498260498, "genuineness": 4.174716949462891, "identity": 0.2755681872367859, "hypothesis": "The 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_Shame/a33ced8baf59c4163f24be61852e480b3aecedc180af9c733036e0dc907b78f0.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "a34bde0a3c8cb3a1f11ea53a26fac832634c602a1ce915387d5a99422105b633", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "022294c8e532696312d973bb28c53513801833266f9932742a09cee143bd0772", "generation_seconds_batch": 20.73585873900447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.585766792297363, "genuineness": 4.375550270080566, "identity": 0.7635554075241089, "hypothesis": "La porte 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_Shame/a34bde0a3c8cb3a1f11ea53a26fac832634c602a1ce915387d5a99422105b633.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "a4237bed2b66ac71b1837e90691e52618f2e0663331a52c788de416b59a5a759", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c759276dc37945d62f3ce89d58e60b1f10b90127fe9765707383920b7c5b5492", "generation_seconds_batch": 16.335660913027823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.2767791748046875, "genuineness": 4.532451152801514, "identity": 0.39436596632003784, "hypothesis": "The 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_Shame/a4237bed2b66ac71b1837e90691e52618f2e0663331a52c788de416b59a5a759.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "a425d7fccfa5dafc3a47c7a10831266fd0df13bb10caa82a1faa4454ecb3a0e8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a036b3ab63ee599b94bafaebf43a4044e5e89b7f39f7523b540cb69d8ff9ee6", "generation_seconds_batch": 20.124654046958312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 6.078212261199951, "genuineness": 4.15588903427124, "identity": 0.6854422092437744, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a425d7fccfa5dafc3a47c7a10831266fd0df13bb10caa82a1faa4454ecb3a0e8.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "a439d336679703d8338431ac03b4a0f391fd0b98f48e712d4964ab5eae859749", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "afd81d4250282f56e354838942d4d24dee66a8d23709a0cabc62d1465b810579", "generation_seconds_batch": 20.128002773970366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 5.911416053771973, "genuineness": 4.444586753845215, "identity": 0.449044793844223, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a439d336679703d8338431ac03b4a0f391fd0b98f48e712d4964ab5eae859749.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "a4d87fbaa3e294e5b85ba70149edc78ba43eb71b7a5552ff4a855c652f48790d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c5f76a8c9a10687f543935dfbd63050160f67286d66766b1132501ac6e1224f4", "generation_seconds_batch": 24.17110184300691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0058201998472213745, "target_z": -0.41406249200232814, "ce": 6.1894097328186035, "genuineness": 4.645420074462891, "identity": 0.3055865466594696, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a4d87fbaa3e294e5b85ba70149edc78ba43eb71b7a5552ff4a855c652f48790d.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "a56651ef5f6bdd9c0f4a731ba742738361cf1a6d250ab9ddbff1ec8714159a12", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "789448e4ba47b224a673a007712ca4beca3db438aa6c5353db18114eba7f0f0b", "generation_seconds_batch": 21.43182792607695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 6.133810997009277, "genuineness": 4.268857479095459, "identity": 0.6117123365402222, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a56651ef5f6bdd9c0f4a731ba742738361cf1a6d250ab9ddbff1ec8714159a12.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "a62a0ab2e6e66d4775a4c4be931db8c8b20dfccd1d426317282ebeda710cf64b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b546602c11df857992434ace287921071ded00404b30dfc568d818cc32df8eaa", "generation_seconds_batch": 19.544922780944034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.205295085906982, "genuineness": 4.281409740447998, "identity": 0.35137027502059937, "hypothesis": "The 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_Shame/a62a0ab2e6e66d4775a4c4be931db8c8b20dfccd1d426317282ebeda710cf64b.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": "a63c81957afa3ea8c9afd6ec1ccddf23599db72e527f78c996f300296c7008f6", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "93c7f62da458d7a741c772166b7564ffcfae03284fa69673bedd1008c2f5211d", "generation_seconds_batch": 17.30650459707249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04842419922351837, "target_z": -0.31054688321982943, "ce": 6.09409761428833, "genuineness": 4.595211505889893, "identity": 0.593650758266449, "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_Shame/a63c81957afa3ea8c9afd6ec1ccddf23599db72e527f78c996f300296c7008f6.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": "a65a5bafef40344b6da73c06f1ecb2c658d59f1f3ef3c6ccf7dbcad1bb05fe87", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92dd25bc144afc053d9f6f756485982560ba5e30af69a18c3dd6586350e5580e", "generation_seconds_batch": 21.26898832002189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053541600704193115, "target_z": -0.3007812495556849, "ce": 5.772419452667236, "genuineness": 4.570107460021973, "identity": 0.5564079284667969, "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_Shame/a65a5bafef40344b6da73c06f1ecb2c658d59f1f3ef3c6ccf7dbcad1bb05fe87.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "a65fb9610ca3f1b047acdc8dbd8911da77cd02be5fe56a2d1192e87811f1b35f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9b9e3483fe4442daf0dd82b86e754191b09b0684a9a87647287485c050fa652a", "generation_seconds_batch": 22.776562015060335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 6.38797664642334, "genuineness": 4.432034492492676, "identity": 0.43972110748291016, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a65fb9610ca3f1b047acdc8dbd8911da77cd02be5fe56a2d1192e87811f1b35f.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "a7859aea7b344cc5daad1950c1acfb7146553f2b4a1bcc623fadc8e65720dc5c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a87c0f5bae9f26a14650f5eb0bdc1b6b8b1eaa7ebd01878f9f63da20e4cb6cc2", "generation_seconds_batch": 20.044352402095683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 6.340320587158203, "genuineness": 4.896461486816406, "identity": 0.6127172112464905, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a7859aea7b344cc5daad1950c1acfb7146553f2b4a1bcc623fadc8e65720dc5c.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "a80395d29368c81dd51be78d60c1a4831b3b4a4476c9d334698d827b30a6710c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ff9212a403bd3ed44d6e505a871090f4b7b88dee2717a794716488f19ab903ad", "generation_seconds_batch": 16.505354143911973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0007028132677078247, "target_z": -0.4042968867743503, "ce": 5.990842819213867, "genuineness": 4.381826400756836, "identity": 0.5264953374862671, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a80395d29368c81dd51be78d60c1a4831b3b4a4476c9d334698d827b30a6710c.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "a81e119c8655c1fe0f2f7937a48989e1333ac3311e7a6c5469d908032d8de1cd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "31ff888d3615874e317104bdae7cb72091bb3d0114b2ce78b0ec5fc51d38c9a6", "generation_seconds_batch": 20.267599397106096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019125431776046753, "target_z": -0.43945311678017057, "ce": 5.879645347595215, "genuineness": 4.432034492492676, "identity": 0.4869171977043152, "hypothesis": "The 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_Shame/a81e119c8655c1fe0f2f7937a48989e1333ac3311e7a6c5469d908032d8de1cd.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "7851bc93a380b28f6b0e20eedb73b0ad1cfa31157f0f0025b136f60cefc2844d", "generation_seconds_batch": 14.847838882007636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007485032081604004, "target_z": -0.38867186722448566, "ce": 6.078212261199951, "genuineness": 4.369274139404297, "identity": 0.5225516557693481, "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_Shame/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "a8d7d39d0d6f5a472dc104e918a49d0a8642d1d1f2bec47a26da2676cb3d768f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "da623d2ba27315e9699330224e8e0ee9176e2ef2c6ea81e3f089133aff6d08f5", "generation_seconds_batch": 14.942114182049409, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 5.772419452667236, "genuineness": 4.507347106933594, "identity": 0.5967768430709839, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a8d7d39d0d6f5a472dc104e918a49d0a8642d1d1f2bec47a26da2676cb3d768f.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "a9062d5586542029520c6df998a8bdfcffd67598666de1bf6497c30182e2f016", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c00c4446cbac8eaa888ccfe6a2c925b3d36553734c6c9876ccc3a12701b57893", "generation_seconds_batch": 20.018955159932375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.780362129211426, "genuineness": 4.419482707977295, "identity": 0.5941643118858337, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a9062d5586542029520c6df998a8bdfcffd67598666de1bf6497c30182e2f016.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "a94016e9eecc28360ea64f1a72d076f5c2b31d3d3db2455a98bd21270a04ec8c", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2dc60451a3924c6fd1a426f1f5225db70839b5202ce504c5ffef1dfbc1c06fa0", "generation_seconds_batch": 15.876464299974032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 5.732706069946289, "genuineness": 4.432034492492676, "identity": 0.6270844340324402, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/a94016e9eecc28360ea64f1a72d076f5c2b31d3d3db2455a98bd21270a04ec8c.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "2292874fa34a2ad4cdfed31fae20ddf17451561c405890adabed21ad9f5b4519", "generation_seconds_batch": 15.011497945990413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.284721851348877, "genuineness": 4.557555198669434, "identity": 0.6511569023132324, "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_Shame/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "aa1e2a2a2f985addf7dec65757dd17171986fbaf54703a60cad658dbf24b24be", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "262c54f9ce9ed7b89b651156d4f40973e1004639280bf2d0ffa43db59ce5d569", "generation_seconds_batch": 23.97847906302195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.340320587158203, "genuineness": 4.137060642242432, "identity": 0.461124062538147, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/aa1e2a2a2f985addf7dec65757dd17171986fbaf54703a60cad658dbf24b24be.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "aa8d047eeee0349f54d61d7bf16e9a994e2004de8fa2c834d8551b48742c1edc", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7c07db2e43082a4c65f089d787c295bf41e84acf6657755f4953f21b3986bfe2", "generation_seconds_batch": 22.829683344927616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04842419922351837, "target_z": -0.31054688321982943, "ce": 5.796247482299805, "genuineness": 4.65797233581543, "identity": 0.3730000853538513, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/aa8d047eeee0349f54d61d7bf16e9a994e2004de8fa2c834d8551b48742c1edc.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": "aaeca97e62553ea9a0284c89486c2d5c3b84cca6bdc64cb6f6695c35937f175c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "1468231155dac7f56a048460bf69dddd83a40a491fe98e46fb891d5f6e8ce706", "generation_seconds_batch": 14.76605577103328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 5.816103935241699, "genuineness": 4.6956281661987305, "identity": 0.6122995018959045, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal. Da legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/aaeca97e62553ea9a0284c89486c2d5c3b84cca6bdc64cb6f6695c35937f175c.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": "ab435217ed10bec6f8020a478e60abc9be110bf3458bf98de03ac14d9fc13957", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "7d104966dec3454094fd662e21ea64b92ea25b9cc4e89286b7639029ea2ddc74", "generation_seconds_batch": 14.950033313944004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05251811444759369, "target_z": -0.30273438766298044, "ce": 5.9431867599487305, "genuineness": 4.507347106933594, "identity": 0.6312628984451294, "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_Shame/ab435217ed10bec6f8020a478e60abc9be110bf3458bf98de03ac14d9fc13957.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "ab4dbffbe818e56b3c0df96bc20d1fa32c80d22167b5d64049350cd3217d1541", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d7bf0b773cbce0261c1dfe44eb0f2e5b6c64b9ca205199178be0a8df1f1bb10c", "generation_seconds_batch": 20.39533399604261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.0146708488464355, "genuineness": 4.231201171875, "identity": 0.7052519917488098, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ab4dbffbe818e56b3c0df96bc20d1fa32c80d22167b5d64049350cd3217d1541.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "ab5a906dbfe77f63a0ead5cb22d54c7e423e67d5bea2b84959fba16efca2c8ec", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fe7b66ad8fc964d4cc5913405019aa8119d7e8a5a23737b59ac0f0ccdda73c2b", "generation_seconds_batch": 14.835922288009897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 6.284721851348877, "genuineness": 4.519899368286133, "identity": 0.5624072551727295, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ab5a906dbfe77f63a0ead5cb22d54c7e423e67d5bea2b84959fba16efca2c8ec.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e05a1f7a17397d3ba8683b0ba85729b66eeecf92469d71def913f67d9e17ad5a", "generation_seconds_batch": 15.082718699006364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.483288764953613, "genuineness": 4.218649387359619, "identity": 0.30438145995140076, "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_Shame/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "abadcb070be95faa20ea85475e10e3019a484dc033170a1aaa7413c656fa17ec", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4c32267c65bbbb385cf8673a705375e6fca48cfe2075dc4b820f20b084d23027", "generation_seconds_batch": 23.500846144976094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 6.348263263702393, "genuineness": 4.758388519287109, "identity": 0.658882737159729, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/abadcb070be95faa20ea85475e10e3019a484dc033170a1aaa7413c656fa17ec.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": "acd23bd58e29a3bc3baa494d9c559b435b1f62c5da3683a4840d4fb633eeb115", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "255a4974b9b3f629d53945c94fc893117a063cc99486dbf68e975057b284d8d9", "generation_seconds_batch": 23.47747438098304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06172943115234375, "target_z": -0.285156258441987, "ce": 5.974957466125488, "genuineness": 4.457139015197754, "identity": 0.6924391984939575, "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_Shame/acd23bd58e29a3bc3baa494d9c559b435b1f62c5da3683a4840d4fb633eeb115.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": "ad0284e5ff249ec44337b2179d869f893d99dae203f78c2c38a7654f3cac13cd", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77655a944d7beb4d1463fd104777f10dbf5eea7c3f7de46f9bc1504be7ed145f", "generation_seconds_batch": 20.22340640099719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06377638876438141, "target_z": -0.2812500106635625, "ce": 5.95112943649292, "genuineness": 3.9927117824554443, "identity": 0.38268375396728516, "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_Shame/ad0284e5ff249ec44337b2179d869f893d99dae203f78c2c38a7654f3cac13cd.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "ad54399d92d7e1e96929fd3c812b3dabe4ab39c093c9a642a2ce3f97316d5fef", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "de067a1f4f85bb0a02f4120731f7b42922eb39dcf03f3062f38222004bd6a877", "generation_seconds_batch": 14.85462025902234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07298770546913147, "target_z": -0.26367188144256903, "ce": 5.5539960861206055, "genuineness": 4.017816066741943, "identity": 0.5389643907546997, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ad54399d92d7e1e96929fd3c812b3dabe4ab39c093c9a642a2ce3f97316d5fef.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "adaa92bca732559913c4fc3b2eb1131a27bfe83d355da7a6e50184ada9fb75a5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "07d0f25df71104c46a1950ee229898e4912c896711a1b7468cfb65b924c54dd6", "generation_seconds_batch": 16.335660913027823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.205295085906982, "genuineness": 4.293961524963379, "identity": 0.40059295296669006, "hypothesis": "The 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_Shame/adaa92bca732559913c4fc3b2eb1131a27bfe83d355da7a6e50184ada9fb75a5.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "6fcfb8d3fe4f9107555aa0f825e0d27a3453105afa05da88e122530291ff5da4", "generation_seconds_batch": 16.892927386099473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 6.205295085906982, "genuineness": 4.231201171875, "identity": 0.6065919399261475, "hypothesis": "Je beri kwam nadat ik vertrokken was? Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "ade3bfca4453cc258db81279f3af7e9f1042a3cf71eec3178507cf7300ab51a4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f2b57434695c1113eac95a01166f1a5e0fc5a3efda7a5a9af33dae39178adad7", "generation_seconds_batch": 16.030965421930887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01810196042060852, "target_z": -0.4375000071090417, "ce": 5.831989288330078, "genuineness": 4.557555198669434, "identity": 0.8486617803573608, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ade3bfca4453cc258db81279f3af7e9f1042a3cf71eec3178507cf7300ab51a4.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "ae078d13b68d75551d91ebc9dc653fc8a6db0215da58f330a4e6e83dee26a5d0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "75a6a788387935d70d4c555eb8ce808be13c1efc7a7268f13795b0499cf2bba2", "generation_seconds_batch": 20.636024457984604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 5.824047088623047, "genuineness": 4.8588056564331055, "identity": 0.740077018737793, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ae078d13b68d75551d91ebc9dc653fc8a6db0215da58f330a4e6e83dee26a5d0.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "62d8800d845b067bc64d9b7c6bc1a1e679ce9de0f01b9d98841ffe53e2c0a809", "generation_seconds_batch": 15.189773167017847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 6.523001670837402, "genuineness": 4.143336772918701, "identity": 0.34095457196235657, "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_Shame/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "ae3285b61210890d8c0c2f1cf90bf98d722b7aea5aa6f5ffc2f91b1c600094fb", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b24fc06c06625f72eb0cd206f80b02212d9158ae2db0d5294d9ea139a9ef59d4", "generation_seconds_batch": 14.62049587292131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.33590608835220337, "hypothesis": "The 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_Shame/ae3285b61210890d8c0c2f1cf90bf98d722b7aea5aa6f5ffc2f91b1c600094fb.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "ae3fe594bda0221d64de70bb19a9b2740913540d39017237223349d8ce060de0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6a24d1256b8dc6f42ecf328397414d8885685c1ac6736ac50d476b9d75dc9a60", "generation_seconds_batch": 16.76211588201113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 6.24500846862793, "genuineness": 4.432034492492676, "identity": 0.7471023797988892, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Oude Raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ae3fe594bda0221d64de70bb19a9b2740913540d39017237223349d8ce060de0.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "ae5ebeb7f29ddd344453b5fe1f937be9f63a2a17ae095485ec40ba28b8fb017f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "78d5b1a201d1181c1282ab7560d7404cf115e02b0ed9a6886fa8cfaca585e13c", "generation_seconds_batch": 20.25151124992408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01810196042060852, "target_z": -0.4375000071090417, "ce": 5.895530700683594, "genuineness": 4.758388519287109, "identity": 0.7018889784812927, "hypothesis": "La porte 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_Shame/ae5ebeb7f29ddd344453b5fe1f937be9f63a2a17ae095485ec40ba28b8fb017f.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "ae774bc4cc8f86c489d1d029721d33da6ecf10bda446432e18d3e2ce48b2c473", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b5bb493dcaabe75df5fb75d651a7768b234cb0aec67fe408ec13ec9710c17958", "generation_seconds_batch": 20.20866179605946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06582334637641907, "target_z": -0.277343762885138, "ce": 5.034743785858154, "genuineness": 4.111956596374512, "identity": 0.44144707918167114, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ae774bc4cc8f86c489d1d029721d33da6ecf10bda446432e18d3e2ce48b2c473.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "ae94a2a167895b73e8aeb12e6ade6b2ba0c3831843091fe5943d38c3669d253c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6abc68b792c2586ebe50b5195748a23ac0198ab5de45a324d251e967988a6f42", "generation_seconds_batch": 20.25151124992408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 5.879645347595215, "genuineness": 4.846253395080566, "identity": 0.8310423493385315, "hypothesis": "La porte 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_Shame/ae94a2a167895b73e8aeb12e6ade6b2ba0c3831843091fe5943d38c3669d253c.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": "af757aa5d46bd50018b0e2dfd8454a00c531cfd7d8c1870c465ee28569958dcd", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "787d72b187d24396fb0bd9571c40508ee934968dc850837fe779f4535553724e", "generation_seconds_batch": 14.57366540597286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 5.609594821929932, "genuineness": 4.042920112609863, "identity": 0.3643328845500946, "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_Shame/af757aa5d46bd50018b0e2dfd8454a00c531cfd7d8c1870c465ee28569958dcd.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "af7b4038ede028b1b9417d4f3223156f5bca3d2d13ce5c8f7e9fedc8febd531f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8000f6c9b2bebd95b51efb33ae1e8a7d3f2ae0abde904be5bbeb984fbc59478c", "generation_seconds_batch": 15.131971598952077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 6.308549880981445, "genuineness": 4.356721878051758, "identity": 0.6726218461990356, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/af7b4038ede028b1b9417d4f3223156f5bca3d2d13ce5c8f7e9fedc8febd531f.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "af8c560b18128b5304b1aeb401ab42cfbc7311bc0e81634fca1369ed92b1ca39", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c7de8d2287c828b0b9f68c19b1cf6fe636ca5ece5072513faf4148a04566da9d", "generation_seconds_batch": 23.550676433951594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.6031540036201477, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/af8c560b18128b5304b1aeb401ab42cfbc7311bc0e81634fca1369ed92b1ca39.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "af9b5b5139a2c629a5f16f9e2913ce5bb8168f06cd3dddb5644e0b0d79444130", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "77b371122150759332a67d8b1bd5cdc9620023a73bde7df2a4ebb8ea5364b128", "generation_seconds_batch": 20.08434561896138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 5.982900142669678, "genuineness": 4.482243061065674, "identity": 0.4986867606639862, "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_Shame/af9b5b5139a2c629a5f16f9e2913ce5bb8168f06cd3dddb5644e0b0d79444130.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "aff440a071de2d24c1c323014bef3b369dc861334d6ac635b142d856b5bec82d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3f358d10364e1751908cdac5d90ee43bf269ca3886b723c81642952b89c1d6d5", "generation_seconds_batch": 20.267599397106096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 6.24500846862793, "genuineness": 4.432034492492676, "identity": 0.42244935035705566, "hypothesis": "The 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_Shame/aff440a071de2d24c1c323014bef3b369dc861334d6ac635b142d856b5bec82d.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "b06f66059401269dd0fe17c4f62f5c904c6a944aca8872b9d9a58245350b428e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "59d2f8fa3446ed74e6505a53b3e154f401936ff77102f8ae679640de918cc040", "generation_seconds_batch": 14.837241639033891, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 5.9431867599487305, "genuineness": 4.557555198669434, "identity": 0.6136299967765808, "hypothesis": "La porte 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_Shame/b06f66059401269dd0fe17c4f62f5c904c6a944aca8872b9d9a58245350b428e.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "b08a708bfb2145d19fefdfb80087119290eda34e315b924ba09422762b0494f2", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "aa6d4ff265dc6cda752c3cc146af0df2b4347b2e72b9eb52025c3b77cfce83ba", "generation_seconds_batch": 17.536916750017554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 5.998785495758057, "genuineness": 4.6203155517578125, "identity": 0.7378453016281128, "hypothesis": "La porte 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_Shame/b08a708bfb2145d19fefdfb80087119290eda34e315b924ba09422762b0494f2.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "b091ccdde039f72f1e0bdfd83ee1eaa976e1308e4523551082a8ae1d2579e87b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "09a5d4ee2d2e08b8c3528b2ab0190fda4eadb79dd38fea132544a4b6afd1478f", "generation_seconds_batch": 19.98656382993795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.078212261199951, "genuineness": 4.833701133728027, "identity": 0.5455596446990967, "hypothesis": "La porte 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_Shame/b091ccdde039f72f1e0bdfd83ee1eaa976e1308e4523551082a8ae1d2579e87b.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": "b0cd138241577600de6c94affee5dd9814a61d03c38b8da6b295cb713086d764", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ede5767026485cd763237d3a7e4cfe20d3314fa06396a1b67da9b2bc8f70399b", "generation_seconds_batch": 23.47747438098304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09192207455635071, "target_z": -0.22753906816501757, "ce": 5.998785495758057, "genuineness": 4.331617832183838, "identity": 0.6848783493041992, "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_Shame/b0cd138241577600de6c94affee5dd9814a61d03c38b8da6b295cb713086d764.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "b0f8dff616bf137fa2a769ffb967e8c96553e1f13f132202caf1b871576ffcc8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c37d8f4791601d3edd6a4d3955f9f2c887f83cfd09e74db8f0c33966ec4f7a6a", "generation_seconds_batch": 20.898360453080386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.292664527893066, "genuineness": 4.293961524963379, "identity": 0.36942532658576965, "hypothesis": "The 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_Shame/b0f8dff616bf137fa2a769ffb967e8c96553e1f13f132202caf1b871576ffcc8.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "b1ca76f59c65650e51038a9e2493a283e0e50128678881a624a93ee0737a4b8b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cea80438298249023e09b10241a0edd850043a97e29c9da55db1cb903457f3ce", "generation_seconds_batch": 22.25768242694903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07605814933776855, "target_z": -0.257812495556849, "ce": 5.7406487464904785, "genuineness": 4.632867813110352, "identity": 0.7647860050201416, "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_Shame/b1ca76f59c65650e51038a9e2493a283e0e50128678881a624a93ee0737a4b8b.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "b25adec25fec48aabd634ed799d291f73db6bc30c22b505c0b77187fd0554a9d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "72c0dfb728d7efa6da955d4d5ac3c4c372a69a750c73fb25b13c6ccbfdd0c422", "generation_seconds_batch": 21.484496903955005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 6.340320587158203, "genuineness": 4.331617832183838, "identity": 0.4175698161125183, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b25adec25fec48aabd634ed799d291f73db6bc30c22b505c0b77187fd0554a9d.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": "b2e212c3974963524f7e87fc105c3b7ce4211729a81c8837165af293f873d400", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "df8afef07a6a3b4b8f442259e7fa4d540cbc06d81ddafebbb74981ed1fa917ec", "generation_seconds_batch": 14.72734099603258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044330283999443054, "target_z": -0.31835937877667836, "ce": 6.23706579208374, "genuineness": 4.024092197418213, "identity": 0.49021443724632263, "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_Shame/b2e212c3974963524f7e87fc105c3b7ce4211729a81c8837165af293f873d400.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "b322019f0e48002eff8ce8abae950fb099322b69a4409323846a1be346c79b1c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "367001c02282b8bfdc3716001e3eb287f97c03e94930eb22a8b368821f7911be", "generation_seconds_batch": 22.973680666065775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 6.149696350097656, "genuineness": 3.9927117824554443, "identity": 0.4183439314365387, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b322019f0e48002eff8ce8abae950fb099322b69a4409323846a1be346c79b1c.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "b385dbb457809f4e592640f97c2681e545b6c27267b9f72048434f772523b40d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3514807577973213292cae767c9b9615b51ac93bad7fa67cd7aa427d2579c754", "generation_seconds_batch": 20.85130067402497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 6.38003396987915, "genuineness": 4.6203155517578125, "identity": 0.47950005531311035, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b385dbb457809f4e592640f97c2681e545b6c27267b9f72048434f772523b40d.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "b3b648a9c113117d233819f715431b8763667aac97ae8004813d873ce2c38af4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bda2aab47eefc2337878b6619262bb5097bf38fc110a2566ed9ad2804cf01227", "generation_seconds_batch": 20.485085262916982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 5.974957466125488, "genuineness": 4.632867813110352, "identity": 0.6908898949623108, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b3b648a9c113117d233819f715431b8763667aac97ae8004813d873ce2c38af4.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "de9e0e10190d6add229670ec457a872d92a863210d4595fde4ba9f31176c65be", "generation_seconds_batch": 16.606683464953676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.340320587158203, "genuineness": 4.532451152801514, "identity": 0.6748030781745911, "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_Shame/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "b42db672fbf9793623dcd588cf36021263c8917a4751ae674a73821e8ff03209", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "99c7f0db7f3d695f9efff8f11ee37ce5035e3552813d7c26aa5577cfd4f5dbbb", "generation_seconds_batch": 21.86258301208727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 6.070269584655762, "genuineness": 4.7332844734191895, "identity": 0.6198831796646118, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b42db672fbf9793623dcd588cf36021263c8917a4751ae674a73821e8ff03209.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "b472d9c8a2622c7a8dc88077375f78b44e601c0bed0504adf461eff012b1981f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "af8d6907ecaff114e751587d563761117e9e226bc9b4113afc1012a030be6366", "generation_seconds_batch": 16.489592397934757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.23706579208374, "genuineness": 4.6705241203308105, "identity": 0.7146817445755005, "hypothesis": "La porte 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_Shame/b472d9c8a2622c7a8dc88077375f78b44e601c0bed0504adf461eff012b1981f.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "b491b3f05b17ebb0a603f482aa98d1bc6be5bec6b12790e0b99bae2927765436", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b818aa767e55bd984a3807eaf2769c5b93c5e562be1a857f56e2de6f5cc6bdd4", "generation_seconds_batch": 20.561961513012648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.165581703186035, "genuineness": 4.406930446624756, "identity": 0.813825249671936, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b491b3f05b17ebb0a603f482aa98d1bc6be5bec6b12790e0b99bae2927765436.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "b4e5bb410ed4ec6ce1ac7efab50a683e09401401126eb34f55bbc2a7d4860226", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "440106a1576e90607c2de1fb841ca129f413b3004d40342455dc8212dd4a4fc0", "generation_seconds_batch": 15.652800529962406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.340320587158203, "genuineness": 4.532451152801514, "identity": 0.2831689715385437, "hypothesis": "The 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_Shame/b4e5bb410ed4ec6ce1ac7efab50a683e09401401126eb34f55bbc2a7d4860226.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "b5679bef1ad44c94ccc964bf8e47d741ea4452504343d01cbde3d2436802ae69", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1e98f47758007d0a44a0d06c14a6c9b289078eba8852ceb6db8246f771c67cff", "generation_seconds_batch": 14.77726627397351, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 5.967014789581299, "genuineness": 4.7458367347717285, "identity": 0.579391598701477, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b5679bef1ad44c94ccc964bf8e47d741ea4452504343d01cbde3d2436802ae69.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": "b5d0f19921aa40e9bd51797b951472ffa15f273bacba3eee6aa65951d81aeb85", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c10973157b014ad273f59df448f15bf31bdadb7932ead48952914c828bd6596", "generation_seconds_batch": 24.312210104078986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 5.927301406860352, "genuineness": 4.632867813110352, "identity": 0.8246292471885681, "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_Shame/b5d0f19921aa40e9bd51797b951472ffa15f273bacba3eee6aa65951d81aeb85.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "b5fb9bbd08fdc70528b3f87faa544a154df275cb4d4cb127a4678b9f2c8962d8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "65e3166594125ac8bfce8f7360565a9bc65f87ddadf211db49d37bc5d941707c", "generation_seconds_batch": 19.63655632501468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 5.569881439208984, "genuineness": 4.105680465698242, "identity": 0.3779768943786621, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b5fb9bbd08fdc70528b3f87faa544a154df275cb4d4cb127a4678b9f2c8962d8.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "b61075bac55ea9d5a4e33e6c92dc9addaca549b4f20c2abba6ed67ac78ffe512", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9bbf63b5d6fcd460965d5f7030bd2e21efced06c4653d347004f6d5c8a887095", "generation_seconds_batch": 14.851595961954445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.982900142669678, "genuineness": 4.293961524963379, "identity": 0.801920473575592, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b61075bac55ea9d5a4e33e6c92dc9addaca549b4f20c2abba6ed67ac78ffe512.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": "b62aa0edc99156232d41a83204cde725e1f1b624fbdb739cb30a6bc9c3383582", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69a9421188a983560aae4a82d164e8bc4c84b75ddc788dbd7018d110f8e3f5a0", "generation_seconds_batch": 20.238516484969296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07196423411369324, "target_z": -0.2656249911136979, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.5148749351501465, "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_Shame/b62aa0edc99156232d41a83204cde725e1f1b624fbdb739cb30a6bc9c3383582.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "b64f51a6de1fff01739971c34c22225883f79c7adc000ee28fc7750304e67846", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0388c325661f74e5e16682c7b540444a9ec58122079ef016eabd0c97bb236290", "generation_seconds_batch": 14.890776955056936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456508696079254, "target_z": -0.29882811144838933, "ce": 6.054384231567383, "genuineness": 4.532451152801514, "identity": 0.6860392093658447, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b64f51a6de1fff01739971c34c22225883f79c7adc000ee28fc7750304e67846.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "b6bf7c152f1799bd6ad764267efb5fbb9f5db01c7a6ad14cd584131e9e7cd354", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c3877027d34f598de604306f9dbddd37438f95710e49e0951e80136b953598d5", "generation_seconds_batch": 21.43182792607695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.038498878479004, "genuineness": 4.15588903427124, "identity": 0.7906898856163025, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b6bf7c152f1799bd6ad764267efb5fbb9f5db01c7a6ad14cd584131e9e7cd354.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "b6e759b7ebe316598576d7d210512c8fdcd533345804fd119d35b301f9ecb787", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6ae3fc334bc676d99df6b3e120964d2bf7ece77c034ecfd922595ff3992fe6e1", "generation_seconds_batch": 20.450252205017023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 5.7684478759765625, "genuineness": 4.7458367347717285, "identity": 0.6575673818588257, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b6e759b7ebe316598576d7d210512c8fdcd533345804fd119d35b301f9ecb787.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "b71bbc15f5e0bfda2906aa1c3c4c0a2220c690821f0c1009379aae31ceb62500", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "669eb3f9ae47a4b30e6496c1f5513f7d14a2f965cc8dacf4a8e604179bbce9f9", "generation_seconds_batch": 22.18106907804031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 5.371314525604248, "genuineness": 4.344170093536377, "identity": 0.5465825796127319, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b71bbc15f5e0bfda2906aa1c3c4c0a2220c690821f0c1009379aae31ceb62500.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "b75d7e34e029f445aee5b55dcc7f33a26baf79c8db02c32d877da80518535d3f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3a9138cf85d65fe1e46675dddad724882c69e783ec3335b3981fd59226178e93", "generation_seconds_batch": 23.71437728893943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.125868320465088, "genuineness": 4.243753433227539, "identity": 0.5676400661468506, "hypothesis": "The 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_Shame/b75d7e34e029f445aee5b55dcc7f33a26baf79c8db02c32d877da80518535d3f.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "b7653ac49f7649265cf57c835c0a785116189b3680acad0c4c3a845307ec8160", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3c60493dcb863ebca6cd53bdae4da287ea37df4a78742b3c2cc3dc82a7013ae8", "generation_seconds_batch": 19.947802798938937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 5.95112943649292, "genuineness": 4.193545341491699, "identity": 0.7272388935089111, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b7653ac49f7649265cf57c835c0a785116189b3680acad0c4c3a845307ec8160.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "b78356d70246c798e0a15ddc508621806c2a01cc8a46bccbbc1fb6d6c605101b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3b620cd86e0bb84185b87550d4f558b051cde400c4cfae229f7364cba7bed836", "generation_seconds_batch": 15.757384749944322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 6.062326908111572, "genuineness": 4.808597087860107, "identity": 0.8372678756713867, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b78356d70246c798e0a15ddc508621806c2a01cc8a46bccbbc1fb6d6c605101b.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "b7c36d467a83200a996f70f19dcd3939eb57d4fcec09e33574e3d5f12284ac1f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "00dfc8ef43e8fa4e5d936c996f1bd130a978ca292aa254e848de4615d3bdf7e3", "generation_seconds_batch": 24.71918791299686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.165581703186035, "genuineness": 4.7081804275512695, "identity": 0.8192991018295288, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre, d'o 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_Shame/b7c36d467a83200a996f70f19dcd3939eb57d4fcec09e33574e3d5f12284ac1f.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "b7c72f567d786f7ddafe54027dd4da39ebaff8d03beaba917335862282d96627", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2073f6d835198f0605f93bdef39e39e5eabb9fae015e34fed033b415d6fb1e5f", "generation_seconds_batch": 16.13053075503558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02321934700012207, "target_z": -0.44726561233701956, "ce": 6.340320587158203, "genuineness": 4.344170093536377, "identity": 0.29423820972442627, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b7c72f567d786f7ddafe54027dd4da39ebaff8d03beaba917335862282d96627.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "b7eb97acac9ba5eeb55866553eb88558746790804caa1c09d5296f91116c9407", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b7e0cf1095a3247b940aa605fe1302c48da86b77a46a9c5266562a0e6e50ce2e", "generation_seconds_batch": 17.79290491808206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0017262846231460571, "target_z": -0.40624999644547916, "ce": 5.7128496170043945, "genuineness": 4.846253395080566, "identity": 0.6841624975204468, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b7eb97acac9ba5eeb55866553eb88558746790804caa1c09d5296f91116c9407.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "b85d62541d993a584b3d26564d30b851e7aa6ebfa0a4f1b35c5dda819d718a74", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "84a2e29b6272bb651779a57c05f96a2691a2a0ee35510014e81c91b7b058298a", "generation_seconds_batch": 19.74090334493667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.585766792297363, "genuineness": 4.319066047668457, "identity": 0.6332899332046509, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b85d62541d993a584b3d26564d30b851e7aa6ebfa0a4f1b35c5dda819d718a74.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "b86d46893da0910f1b525f0fffd66b44530408339d93039dab2bfb2a89f97ded", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e5797fb23ff98d2c1ae7bcd597fb77d362c7cd3e4694ef7c49249358137f61cc", "generation_seconds_batch": 16.048846506979316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0320485383272171, "target_z": -0.34179686544722526, "ce": 5.6532793045043945, "genuineness": 4.344170093536377, "identity": 0.6038128137588501, "hypothesis": "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_Shame/b86d46893da0910f1b525f0fffd66b44530408339d93039dab2bfb2a89f97ded.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "b8feb19b7f0fca47d0abf32278611a55cd3fe24f6e666ba47c088d3fe9743110", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1913a8a3b213d76c5d63de81adcb5d80ab04aa48ca54329f5b01853574f89ea0", "generation_seconds_batch": 22.354902556049637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 5.4825119972229, "genuineness": 4.557555198669434, "identity": 0.454892098903656, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b8feb19b7f0fca47d0abf32278611a55cd3fe24f6e666ba47c088d3fe9743110.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "b98dc67519c6e2ffdc815e13af57b3290b7b64515ca9be8c925e872339c085d3", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5536433ff672292d2895e4bbf33d82a0ea1f18844027e36fff3c88a01d65594a", "generation_seconds_batch": 16.68988438800443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.6657180190086365, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b98dc67519c6e2ffdc815e13af57b3290b7b64515ca9be8c925e872339c085d3.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "b992a3ba893eac190128c5ac7f15ea44aa35d232046f86c2fa12e8c37c3fedaa", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f44721717df4f1ecd980560a4dba11d289923abeb02e2b8f95f665a6772b8dbc", "generation_seconds_batch": 24.356543152942322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 6.308549880981445, "genuineness": 4.532451152801514, "identity": 0.5458675622940063, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b992a3ba893eac190128c5ac7f15ea44aa35d232046f86c2fa12e8c37c3fedaa.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "b9ebe8763e89b9ec29cb4e63c38ba3ba46bc40c8d00e64c4cd6eb4811000240e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7f8f0dbc4915211d540daad441cbaf518dacac0eb519deaedcb9729ba1919bcd", "generation_seconds_batch": 20.33966451708693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456508696079254, "target_z": -0.29882811144838933, "ce": 5.4666266441345215, "genuineness": 4.281409740447998, "identity": 0.4554673135280609, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/b9ebe8763e89b9ec29cb4e63c38ba3ba46bc40c8d00e64c4cd6eb4811000240e.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "ba052012485d2b903946ecf9312e522d1432b1520bbeb5fb75c4de3ba0e50d77", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fdb2cbe823ec43a32596d1b7b029f6cca797f7872695a0160133c7cef59da826", "generation_seconds_batch": 23.169508755905554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.062326908111572, "genuineness": 4.645420074462891, "identity": 0.5651662349700928, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ba052012485d2b903946ecf9312e522d1432b1520bbeb5fb75c4de3ba0e50d77.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": "ba11158400bd88797ed9e4689601547fd86e1028e1812a342d30d3824978588a", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "075f1d5508b8424ecf215af13f4b7579a55b471e287a86616b93732977c485c4", "generation_seconds_batch": 22.69971148110926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06991727650165558, "target_z": -0.2695312388921224, "ce": 5.816103935241699, "genuineness": 4.3127899169921875, "identity": 0.5106399059295654, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir pu. 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_Shame/ba11158400bd88797ed9e4689601547fd86e1028e1812a342d30d3824978588a.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "ba57454ec570f7f4b9668f05974a9fb87919cc1c8387665bdeb54222650e8cac", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1a7aec45df2170575217b6f290152ff622254febb61657b690838e91a024024d", "generation_seconds_batch": 19.609599447925575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0023676306009292603, "target_z": -0.3984375008886302, "ce": 6.006728172302246, "genuineness": 4.457139015197754, "identity": 0.4470042884349823, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ba57454ec570f7f4b9668f05974a9fb87919cc1c8387665bdeb54222650e8cac.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "1700860c7f252b28c270fd32fc7fcce06bd08c13faf99eae94c6020041604d3b", "generation_seconds_batch": 15.024872343987226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.149696350097656, "genuineness": 4.469690799713135, "identity": 0.7438388466835022, "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_Shame/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "ba72156ab1d8130de6a29fc5ece8c706d4a83f73fefab2f51fab871646c3b42b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a8575e852a00a9b010847ab72dbb93f8128a1d8615302721aea3cb1fa633070a", "generation_seconds_batch": 20.10425465996377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05865900218486786, "target_z": -0.29101561589154035, "ce": 5.919358730316162, "genuineness": 4.143336772918701, "identity": 0.2486329972743988, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ba72156ab1d8130de6a29fc5ece8c706d4a83f73fefab2f51fab871646c3b42b.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "bb08805d00c0e8a10b4acce22614c93f6cffbe4fa9c5c306f6cdef05ade7991a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "31c337bb420af549b7974586ed834a00e1741bff3d0411596fbb38025a662237", "generation_seconds_batch": 14.926657047937624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010937601327896118, "target_z": -0.42382812566647265, "ce": 5.935244083404541, "genuineness": 4.720732688903809, "identity": 0.7171853184700012, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/bb08805d00c0e8a10b4acce22614c93f6cffbe4fa9c5c306f6cdef05ade7991a.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": "bb208a12cfbe4e017afcc01f846fc1cabf83281a199cbc5fdaa7700ff872f488", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "5d012c033a3783387ac887c50c620ee308e75a1417ae30ba04799c75460ced84", "generation_seconds_batch": 15.469032479915768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07605814933776855, "target_z": -0.257812495556849, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.6694871187210083, "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_Shame/bb208a12cfbe4e017afcc01f846fc1cabf83281a199cbc5fdaa7700ff872f488.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": "bc82e1fd6c840b1b0a7840c13b5f816cdf146817312a9dd7d7f3fc7a02893bf1", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "e759a610b640e1addea05b4f73fb47d3daae1e4f90ae6944fd33423cab546ae4", "generation_seconds_batch": 14.466073184972629, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 5.6254801750183105, "genuineness": 4.425758361816406, "identity": 0.4938480257987976, "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_Shame/bc82e1fd6c840b1b0a7840c13b5f816cdf146817312a9dd7d7f3fc7a02893bf1.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": "bc9adbfd0960453ea7011de266d16f5165003aec86e10c93dadc7a421eee950b", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7c55e4dd2500250a4e7715cb3e20572988c5609d5568903f32956c8925d62c76", "generation_seconds_batch": 16.42840678000357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06377638876438141, "target_z": -0.2812500106635625, "ce": 5.593709468841553, "genuineness": 4.13078498840332, "identity": 0.7744102478027344, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/bc9adbfd0960453ea7011de266d16f5165003aec86e10c93dadc7a421eee950b.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "bca24db22b20fb30a804c1199de8f9c6066075dbd8bc5c22615f50146611c051", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "be93d5030188dde04eb20cf93436844e5118a2c240c2de7cfcb7d7cc01724bb1", "generation_seconds_batch": 18.829043264035136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 5.990842819213867, "genuineness": 4.934117794036865, "identity": 0.6854496002197266, "hypothesis": "La porte 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_Shame/bca24db22b20fb30a804c1199de8f9c6066075dbd8bc5c22615f50146611c051.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "bcafd58ca4926cfa10d7aa13f04bcb22932d4cb05dadd03fb4ccf8dac60a5dc0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e1af26bcb84f93345bb8a306dd7c5993e88307cd2375c4e40655ddadb76d8bb5", "generation_seconds_batch": 15.479991476982832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042283326387405396, "target_z": -0.3222656265551029, "ce": 6.229123115539551, "genuineness": 4.419482707977295, "identity": 0.7163394689559937, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/bcafd58ca4926cfa10d7aa13f04bcb22932d4cb05dadd03fb4ccf8dac60a5dc0.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "bcc5fc35a6797b0fcc3642e8bccd9b27f0bf562bc4f5ca193633857dabd3d78f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2efc59e9af7309b80c1ab3e3a6986d5561405ed5a5228ed3cb01e7456f9dc410", "generation_seconds_batch": 20.48269936197903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0058201998472213745, "target_z": -0.41406249200232814, "ce": 6.213237762451172, "genuineness": 4.570107460021973, "identity": 0.5357775688171387, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/bcc5fc35a6797b0fcc3642e8bccd9b27f0bf562bc4f5ca193633857dabd3d78f.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": "bceb414323070af73315b1246eb9592828297b70ec439d230171580b7cf4bbf6", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf7c5eb7bf12276d8386db4c4e8f3bcbb3003a66215f8d928a06d85fb4fb2053", "generation_seconds_batch": 17.745785551029257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.5937519669532776, "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_Shame/bceb414323070af73315b1246eb9592828297b70ec439d230171580b7cf4bbf6.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "be4fdf423750042bc05bcf00d0421f2056a41549c91d378d2f99d0706538ccd5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ca4e30b4472a9c1ffe74a96fbb6f03776239eaeb43b2a463199dd9feb28ab9ab", "generation_seconds_batch": 22.40669416298624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 5.4825119972229, "genuineness": 4.193545341491699, "identity": 0.3726164996623993, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/be4fdf423750042bc05bcf00d0421f2056a41549c91d378d2f99d0706538ccd5.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "be7dbbe83fb957cbc24a751ebe0d04b1d81db43f03de692ac410f842ac28e91f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dbba5099293c1c618bffef3a8635f26bf5d4968875cf0fc0f03534f90805be3b", "generation_seconds_batch": 20.251263079000637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 5.895530700683594, "genuineness": 4.042920112609863, "identity": 0.3116869330406189, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/be7dbbe83fb957cbc24a751ebe0d04b1d81db43f03de692ac410f842ac28e91f.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "bea61f2a3952e5f2889dc3af5cce7833e4ed5982768db49258354c0d889d18b0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a9205e96cd1ab5f06c0c0ae6b233d5f8d033a5b20b8ee2dcc1aac771b94d02e4", "generation_seconds_batch": 19.937134218984284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.95112943649292, "genuineness": 4.532451152801514, "identity": 0.7833436727523804, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/bea61f2a3952e5f2889dc3af5cce7833e4ed5982768db49258354c0d889d18b0.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "bea764a085e9fca4c57e2f3edd27984d5330160bc8708529b5f0f91c552ae374", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "612aa13c958694cc1f00dbe39064f970bc66ee6e62aa8da5ac0e2300af3ead92", "generation_seconds_batch": 20.76856239303015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.038498878479004, "genuineness": 4.532451152801514, "identity": 0.4661581516265869, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/bea764a085e9fca4c57e2f3edd27984d5330160bc8708529b5f0f91c552ae374.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "bec9b8e62c208b0075c6e8d3533999308003e16b83e74ecf223cd2857f0d249e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6f1af377d0406db02e3dd5db264baabe0ef2f5336800848682e89f0f87bde452", "generation_seconds_batch": 20.81881781190168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 6.078212261199951, "genuineness": 4.7332844734191895, "identity": 0.7947009801864624, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/bec9b8e62c208b0075c6e8d3533999308003e16b83e74ecf223cd2857f0d249e.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "bf8bbe330b2ba97dbf9763a3ac3b5068ae8ede39fdf1a25625704abf3cb8270b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "276b5e51c2ef6804c2537582bf9e1427f0211b60a160294d67fded6b3ab8f79a", "generation_seconds_batch": 20.232087623910047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06377638876438141, "target_z": -0.2812500106635625, "ce": 5.8875885009765625, "genuineness": 4.808597087860107, "identity": 0.7991528511047363, "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_Shame/bf8bbe330b2ba97dbf9763a3ac3b5068ae8ede39fdf1a25625704abf3cb8270b.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "bf967bd2838b2a442ef0439920a36cf1114ef06da8c73e9b337e440bb906eece", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a3e580458be4642ad23b62016b4e1689c2250298881881999dbf49f1c9583d21", "generation_seconds_batch": 20.802230881992728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.1894097328186035, "genuineness": 4.319066047668457, "identity": 0.3798013925552368, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/bf967bd2838b2a442ef0439920a36cf1114ef06da8c73e9b337e440bb906eece.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "c00c9fadf4828017e117c86a2f51db31312b1cdeb15895e79ff8dbb1c2124091", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "90ff19f79fefe8b28bc0fce09354bae7c3cb58856e39c74894d438c1191bea0c", "generation_seconds_batch": 21.526654524030164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.5583775043487549, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c00c9fadf4828017e117c86a2f51db31312b1cdeb15895e79ff8dbb1c2124091.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": "c150a19e3a217aa10bbe009612c7737f9a06da8811845c5629c9cfb73b3ed314", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "77578f721c986ebc8226afe8d05e12a0ab84f198af467de136ee65beaac8f1f6", "generation_seconds_batch": 14.846746501047164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024242833256721497, "target_z": -0.4492187504443151, "ce": 5.919358730316162, "genuineness": 4.432034492492676, "identity": 0.6139236688613892, "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_Shame/c150a19e3a217aa10bbe009612c7737f9a06da8811845c5629c9cfb73b3ed314.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "c17b22d4519519c6081de1b425bb23683219cb38604ca00a4864ebc37da03b35", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "41315268a0ab0252d3123389f1a72d4f9f6c75ad16dfb1dee99e68ed5c3bdabe", "generation_seconds_batch": 21.68781935609877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042283326387405396, "target_z": -0.3222656265551029, "ce": 6.284721851348877, "genuineness": 4.65797233581543, "identity": 0.4222792983055115, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c17b22d4519519c6081de1b425bb23683219cb38604ca00a4864ebc37da03b35.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "c1d5ef411f88ddf501bd5adc33a4e2552c6ccfd19faf8fb7b333e554ddfe052f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3607219c753d96fb5647c847d69ec0f26afba8a81a8d9ef86d08e3552480bb1d", "generation_seconds_batch": 20.25545775797218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012984558939933777, "target_z": -0.4277343734448971, "ce": 5.895530700683594, "genuineness": 4.758388519287109, "identity": 0.5811668634414673, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c1d5ef411f88ddf501bd5adc33a4e2552c6ccfd19faf8fb7b333e554ddfe052f.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "c24cd889c330e197225bdc03ebf7a2bae33b5aba1bf70c70c437c739bb054915", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ea2cb27692c66f9a49b4cc52f4d45e603b73c18f5cc0a031bc8478254a7c8863", "generation_seconds_batch": 19.544922780944034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04637724161148071, "target_z": -0.3144531309982539, "ce": 5.927301406860352, "genuineness": 4.231201171875, "identity": 0.5660784244537354, "hypothesis": "The door is still open. I I 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_Shame/c24cd889c330e197225bdc03ebf7a2bae33b5aba1bf70c70c437c739bb054915.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "c288a7fb5ddb98e62afb92a03693c67567a5da0231621b64425b8d8637ba985f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7e96cda9cc8574e843787a293517ab9f6282b83b16d6be75141c6986a34421ed", "generation_seconds_batch": 16.980711470008828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.71682071685791, "genuineness": 4.344170093536377, "identity": 0.4886159300804138, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c288a7fb5ddb98e62afb92a03693c67567a5da0231621b64425b8d8637ba985f.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "c291036f9acd33270870c2cd616b538c1cc7f7a91cfb78def612f5fbd6d9a8f0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "87a30db442f1925bc5d85372c33d9727ee903d0a8ae48ca5bf1a9b8d01a3ebe1", "generation_seconds_batch": 19.97506153397262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 5.601652145385742, "genuineness": 4.256305694580078, "identity": 0.3169710040092468, "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_Shame/c291036f9acd33270870c2cd616b538c1cc7f7a91cfb78def612f5fbd6d9a8f0.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "663e766f71248ab6c7dbb70376822b3c10b8ae9cb7dbfab42b90a8bf4957b296", "generation_seconds_batch": 15.217378493049182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.046441555023193, "genuineness": 4.306513786315918, "identity": 0.7012501955032349, "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_Shame/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "c3a236ac3a998bb77dd64d37020b0c1ca40a42ab683553dd6fab75e746de70f9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0ff6809ec82195840cf02d5818715d7879655931029d043b676fe2073cd88980", "generation_seconds_batch": 22.560060454066843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.284721851348877, "genuineness": 4.645420074462891, "identity": 0.5740200281143188, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c3a236ac3a998bb77dd64d37020b0c1ca40a42ab683553dd6fab75e746de70f9.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "c3ad0a2ad4911a8d930b1bbda06cc0b97d528496b5457e0554e679d95588d837", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "877eaedd3259d5ba707223d8b1c85de14ead809a5635e6e8a39d87225fe343eb", "generation_seconds_batch": 23.97847906302195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.300607204437256, "genuineness": 4.419482707977295, "identity": 0.6862211227416992, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c3ad0a2ad4911a8d930b1bbda06cc0b97d528496b5457e0554e679d95588d837.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": "c3c2a9d09f2a733b6646b4eec8a1c714dd00cb28fd6bbf9dd766de647d621c97", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "150628b2b9839c33362f8b0905d796383e48a5e2841efcf14cfdb2a4b7a3d82c", "generation_seconds_batch": 14.571717766928487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02321934700012207, "target_z": -0.44726561233701956, "ce": 5.6532793045043945, "genuineness": 4.162164688110352, "identity": 0.5599861145019531, "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_Shame/c3c2a9d09f2a733b6646b4eec8a1c714dd00cb28fd6bbf9dd766de647d621c97.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "c3f4e39b51a251d5fda8bd3106ce37a87c95a3268ffd9e79aba23debd496abd5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cc0a18dbd7f7f383de1a131d2b772192261a6856f9eccb4011256f6852246ccb", "generation_seconds_batch": 20.32518943992909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.569881439208984, "genuineness": 4.3504462242126465, "identity": 0.5780531167984009, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c3f4e39b51a251d5fda8bd3106ce37a87c95a3268ffd9e79aba23debd496abd5.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "c4260e634df74fcc93e0d9f3d888fe9d99c3bf6d575a82bf4afcca74906eade0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "183610349ee3fa138dbd5397ce21a0c59c69cf62de6077fdf9a60444698d94bf", "generation_seconds_batch": 20.75440801505465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 5.935244083404541, "genuineness": 4.193545341491699, "identity": 0.4974045157432556, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c4260e634df74fcc93e0d9f3d888fe9d99c3bf6d575a82bf4afcca74906eade0.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "8f00d8ebb74c233e7445be2ee39df9d3cb522cc99f19cabf6f6c64e99b9ed39a", "generation_seconds_batch": 14.722314605955034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.8010941743850708, "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_Shame/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "c593ce2256e1b7ec8935654a75b123c787030d439f824b939c6b9eefeab1759b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ae2e0ce82db8e8ebddd419cd313e91a2b88552af5e86d88c2788513c295c8b00", "generation_seconds_batch": 21.848724526003934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 5.847874641418457, "genuineness": 4.080576419830322, "identity": 0.5660040974617004, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c593ce2256e1b7ec8935654a75b123c787030d439f824b939c6b9eefeab1759b.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "c598b1579e07b60f0268f3ee72a299966e321a312e88e963240bd129e4f63308", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1e582cb432751fe7ed6e716bebf0061787fa39b4881480cee875899133e74342", "generation_seconds_batch": 15.457615832099691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 5.780362129211426, "genuineness": 4.582659721374512, "identity": 0.6681386232376099, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c598b1579e07b60f0268f3ee72a299966e321a312e88e963240bd129e4f63308.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "c5d5a641d14183cfb3aa87c5aab7d2b2f30abbeaca292a068641f274987d7c73", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "01f0df940b38496d440082aa33b69695a7e7bdbf5df90675285b84a00d2a7c98", "generation_seconds_batch": 20.545681989984587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.23706579208374, "genuineness": 4.833701133728027, "identity": 0.8074837923049927, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c5d5a641d14183cfb3aa87c5aab7d2b2f30abbeaca292a068641f274987d7c73.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "c5fe7374feaa11b3355d77a2f0d970d2d40f1f2a889bae259aac2cac493e6b28", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "df445f9a5e048300967e8ccbbb14c36aa1fbcd4e5afe5d4065b5e679ce4b3599", "generation_seconds_batch": 16.945818534004502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.08517609536647797, "hypothesis": "De deur staat nog open. Ik heb je jas. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c5fe7374feaa11b3355d77a2f0d970d2d40f1f2a889bae259aac2cac493e6b28.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "c635c60e4a5507c8ab606d4edb8078c6a1f3a6f8a6369b6b8b7870b1922fac29", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8798b69045c36fa4e07648f1f92a9c9b349e57327347c9eb0148bbe03c4d0305", "generation_seconds_batch": 21.683173026074655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 5.871703147888184, "genuineness": 4.507347106933594, "identity": 0.6345065832138062, "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_Shame/c635c60e4a5507c8ab606d4edb8078c6a1f3a6f8a6369b6b8b7870b1922fac29.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "c6711c87d0c572259bd1bacfb5f7c502f79fcac44717aa27c5339e65958efb71", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c722f8234fed326ca58f2baf9821707cdb9b190a14a36491f02c8679d485e341", "generation_seconds_batch": 18.137261481955647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.252951145172119, "genuineness": 4.469690799713135, "identity": 0.3997458815574646, "hypothesis": "The 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_Shame/c6711c87d0c572259bd1bacfb5f7c502f79fcac44717aa27c5339e65958efb71.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "c6735ab0e1c0401a658c28f136c4988167ae5d759cea3061fa06420293290923", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4ca815a06aab6a5fdbaf24f21c16b07b6be9a7ccf13ea7dd34ea4ad4ad0bb62c", "generation_seconds_batch": 15.787676666979678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.213237762451172, "genuineness": 4.532451152801514, "identity": 0.6002829670906067, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c6735ab0e1c0401a658c28f136c4988167ae5d759cea3061fa06420293290923.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "c7bad27a40ccbad7a9064a5d0e3e2784662f4ff196ea0a747e2e29e6207671c9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d4a52779c8f8d9d4fecaa85b26d9110b1f649694dfa8e865e0e62deed3c251a9", "generation_seconds_batch": 22.781461987062357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03818941116333008, "target_z": -0.3300781221119518, "ce": 5.998785495758057, "genuineness": 4.482243061065674, "identity": 0.6328308582305908, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c7bad27a40ccbad7a9064a5d0e3e2784662f4ff196ea0a747e2e29e6207671c9.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "e978b6ab5c75856507b39609605a0bb7ee6c6d8fbdb41ef1b229b741e1b429f8", "generation_seconds_batch": 16.892927386099473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 6.109982967376709, "genuineness": 4.293961524963379, "identity": 0.42570018768310547, "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_Shame/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "b4f41657e2a4213e178708ce5e3ee264d00e732e5e7e773793e68430aa851c14", "generation_seconds_batch": 15.616806780919433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 6.419747352600098, "genuineness": 4.570107460021973, "identity": 0.3357676565647125, "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_Shame/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "c91d3362e939d3057e36f9578f3224588b0e32fd8979265cc4b09584fc427464", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3a3b2a456f1f952dc76d680bce28e55b2bbcaa47b68ee3760dcd978f3b41a1b", "generation_seconds_batch": 14.7705800520489, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 5.831989288330078, "genuineness": 4.607763767242432, "identity": 0.28416210412979126, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c91d3362e939d3057e36f9578f3224588b0e32fd8979265cc4b09584fc427464.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": "c93f141c942ef941ecd83275722bb1bb5634a1179291cfc237ba3fe4404332cc", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "50eb060aff1e622a5a547afd49cb6b42c660373589ea9d64a5b0b98451eeb2e5", "generation_seconds_batch": 14.950033313944004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 5.708878040313721, "genuineness": 4.319066047668457, "identity": 0.8444559574127197, "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_Shame/c93f141c942ef941ecd83275722bb1bb5634a1179291cfc237ba3fe4404332cc.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "c9557778a2b4d7b4efb150838ccaab08b79f03bfbaf3deeaa60e472f6390695a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d23a3dbdc34eb17202a6f3aeaf13121e9a53fca7f13459cba786172f4dfc7fd0", "generation_seconds_batch": 15.152022249996662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0007028132677078247, "target_z": -0.4042968867743503, "ce": 6.23706579208374, "genuineness": 4.394378662109375, "identity": 0.4910438060760498, "hypothesis": "The 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_Shame/c9557778a2b4d7b4efb150838ccaab08b79f03bfbaf3deeaa60e472f6390695a.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "c9add50158758e27aaabbd8fda7efa653708d9622f68771deffaad0255318983", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c1412f29488b9984fad7420ff7897fa3851d17a02e651c1d7269f81ce832ee69", "generation_seconds_batch": 15.133816722081974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 6.308549880981445, "genuineness": 4.507347106933594, "identity": 0.3971608877182007, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/c9add50158758e27aaabbd8fda7efa653708d9622f68771deffaad0255318983.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "ca08832546a458ddc51d1fa212cae6bbd956453f3b1bd945008313467854fe93", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f2f23ecfb977f2f3d011fafd2337cee4f3ee20d3c31a58c988f005a873bcacb9", "generation_seconds_batch": 20.041249466012232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01810196042060852, "target_z": -0.4375000071090417, "ce": 5.831989288330078, "genuineness": 4.770940780639648, "identity": 0.6651439666748047, "hypothesis": "La porte 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_Shame/ca08832546a458ddc51d1fa212cae6bbd956453f3b1bd945008313467854fe93.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "ca4cd6796cf0840348b527ea93fa1a3d1c2aa9106484dc85475fce6e1b98ea70", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b0706c1c50349e3e488e05c7507a09b915bf80644fb082d68883a6e6aa76641b", "generation_seconds_batch": 21.68781935609877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.0146708488464355, "genuineness": 4.632867813110352, "identity": 0.5297210216522217, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ca4cd6796cf0840348b527ea93fa1a3d1c2aa9106484dc85475fce6e1b98ea70.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "ca58fe75ee093944f058e0de73e6a64ee341101664fed726d07ef5f946943d19", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "08bb6fbd30cf0a5d4fca08f482e3b914bc86bc18056e5728b818e5009ed7604c", "generation_seconds_batch": 19.955406173015945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 5.8875885009765625, "genuineness": 4.770940780639648, "identity": 0.7900621891021729, "hypothesis": "J'ai trouvé la 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_Shame/ca58fe75ee093944f058e0de73e6a64ee341101664fed726d07ef5f946943d19.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "cac5df69e59942b5d35d66797948a88347acfe268f79e54238ff49c65df3d4bf", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9b47d993757a18dd72f2dd9b640685c1dd535567c22f550fd123130889fe6ff2", "generation_seconds_batch": 19.885064350091852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 6.054384231567383, "genuineness": 4.281409740447998, "identity": 0.6308534741401672, "hypothesis": "The 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_Shame/cac5df69e59942b5d35d66797948a88347acfe268f79e54238ff49c65df3d4bf.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "cb2adb91bc1f46116b15e0d1ff53c56071ff1bc5496f033521b8ae34f41aa768", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c26f771e10cdc838c62210debcd2ddbb1393fe28214ecad10030290d367675f9", "generation_seconds_batch": 17.151193268946372, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07196423411369324, "target_z": -0.2656249911136979, "ce": 5.871703147888184, "genuineness": 4.7081804275512695, "identity": 0.6048177480697632, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/cb2adb91bc1f46116b15e0d1ff53c56071ff1bc5496f033521b8ae34f41aa768.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "cb39771bb3b03bf47de14866a8a2bd4175130f2de110ee68e93ad29293dc86c4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "769facb7cb2a6816b2f4d39dd990af4306b59e30d83796fb513e559db86aca6b", "generation_seconds_batch": 20.32518943992909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 5.661221981048584, "genuineness": 4.369274139404297, "identity": 0.4585459232330322, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/cb39771bb3b03bf47de14866a8a2bd4175130f2de110ee68e93ad29293dc86c4.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "cb555b37d63a74ce21f3e7a0106eac4ed61e78585efe7582961c136279bfa161", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0f6a080046cc59128a277d8703df79574c1bc72c3269658028be06045880039a", "generation_seconds_batch": 21.848724526003934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.41395798325538635, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/cb555b37d63a74ce21f3e7a0106eac4ed61e78585efe7582961c136279bfa161.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "ccaaf8c89141a6d8204fbf3517314d4f7ae887b21903aa7ac28362d5c2d0d17c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f86bad0a4c825e25890787da69d9cf3db5373688ec9f3bcc9775f0e45bf92d6d", "generation_seconds_batch": 20.03495441004634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.308549880981445, "genuineness": 4.243753433227539, "identity": 0.3404737710952759, "hypothesis": "The 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_Shame/ccaaf8c89141a6d8204fbf3517314d4f7ae887b21903aa7ac28362d5c2d0d17c.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "ccfa6253bee8ec2eb5020efab570d3c54eff9e97fb3cdd3dd610b43c83dff92f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b0848024b8e93667cf90312d8be933b47be2483c1cf03623c5719a5d67495ab3", "generation_seconds_batch": 21.562861543963663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06787031888961792, "target_z": -0.2734374866705469, "ce": 6.0305562019348145, "genuineness": 4.331617832183838, "identity": 0.5082281827926636, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ccfa6253bee8ec2eb5020efab570d3c54eff9e97fb3cdd3dd610b43c83dff92f.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": "cd45023e559f88fdfd06f83ee5bb9a0c4b944d4762e47fc7077d190edfe9d809", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2e933628dfe4fb25ad6175d1588fd8705f216aa346dd8b8f31d092cb31855406", "generation_seconds_batch": 14.537745066918433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.1020402908325195, "genuineness": 4.469690799713135, "identity": 0.4547010660171509, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/cd45023e559f88fdfd06f83ee5bb9a0c4b944d4762e47fc7077d190edfe9d809.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "cd82ea080913953300cab3e5f8ec864a6b36cbdece4693e00dbea45ff067f20c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bf7eeb854205c2e9651d8b60eb76632be14dd07f3157ac8b89a489faf1138612", "generation_seconds_batch": 20.085721159004606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0017262846231460571, "target_z": -0.40624999644547916, "ce": 6.09409761428833, "genuineness": 4.3881025314331055, "identity": 0.47395771741867065, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/cd82ea080913953300cab3e5f8ec864a6b36cbdece4693e00dbea45ff067f20c.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": "cddefc184bca7530a22c0664d7bbfa0dacfd81690af38b3f4b37a388f0f1e85e", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc68b273a93c7f6d04bf9415b62c8cf2f7ff3911c052d850e90f9f26608d0027", "generation_seconds_batch": 22.96394300099928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.141753673553467, "genuineness": 4.319066047668457, "identity": 0.6792861819267273, "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_Shame/cddefc184bca7530a22c0664d7bbfa0dacfd81690af38b3f4b37a388f0f1e85e.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": "ce159615a4c3cb8ab9b0f266a350c124e5e72499a31071f8c75939836c210d61", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "f6f24258b2839be25be0abd8c9578c51e25ccccb3165b81c4a0bd04a73423f55", "generation_seconds_batch": 17.301141466014087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.221180438995361, "genuineness": 4.268857479095459, "identity": 0.5031311511993408, "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_Shame/ce159615a4c3cb8ab9b0f266a350c124e5e72499a31071f8c75939836c210d61.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": "ce79fa9d212426f244597a9e32ecc5205201d8504c97c5f6223ee0617d5012ab", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "e1a0d7dd46a019d54b1b270330645b0306201ae6ea04990fcf19af43a98a6f5c", "generation_seconds_batch": 14.457030951976776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06172943115234375, "target_z": -0.285156258441987, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.7851462364196777, "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_Shame/ce79fa9d212426f244597a9e32ecc5205201d8504c97c5f6223ee0617d5012ab.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "ce8b23d7b5755cbc830f1704272e5eda1239be2cd1043a02b4aba8873969d25b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a53b92e37bdbf222d476e7a3e9331b1b1d876827baaa17b702ce65f7df6f2657", "generation_seconds_batch": 21.408640939975157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03818941116333008, "target_z": -0.3300781221119518, "ce": 5.816103935241699, "genuineness": 4.419482707977295, "identity": 0.39904800057411194, "hypothesis": "He encontrado la cajita. Estaba junto. a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ce8b23d7b5755cbc830f1704272e5eda1239be2cd1043a02b4aba8873969d25b.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "ce943f65c1ab75812dadfaba419339d671ef0fc8c9c41cad14eb8d1c42223217", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0ad58cb9bf504f98f891b0396d195c0a23b378f0c0e727806287e6dd1fa5ed21", "generation_seconds_batch": 20.55255846399814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.252951145172119, "genuineness": 4.281409740447998, "identity": 0.3814709186553955, "hypothesis": "The 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_Shame/ce943f65c1ab75812dadfaba419339d671ef0fc8c9c41cad14eb8d1c42223217.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "cec726de5e381bd79cb30bdcb29ba7d7b363ce9c8d3bd9c00929bb02972f7951", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "30a8c14594deaa881f2d2d1d99888e16e5507afd1e686a4f555714c64a0f837b", "generation_seconds_batch": 16.188317687017843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06991727650165558, "target_z": -0.2695312388921224, "ce": 6.0146708488464355, "genuineness": 4.796044826507568, "identity": 0.596744179725647, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/cec726de5e381bd79cb30bdcb29ba7d7b363ce9c8d3bd9c00929bb02972f7951.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "ced029b43d48312c6c36c8ec59d02999f5ea87c30ef00a1bb1b6a6b25e0fab71", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "872715b5c6119e642bb0835890bf38e0e4a1997676ff3bc6414147f063530b41", "generation_seconds_batch": 15.787676666979678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 6.2767791748046875, "genuineness": 4.545003414154053, "identity": 0.7276239395141602, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ced029b43d48312c6c36c8ec59d02999f5ea87c30ef00a1bb1b6a6b25e0fab71.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "cefb01669376124df0e040ad73ab52bb657438e2e5f0be9541f87a715c4e8308", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eba166cf70fe65f8f32b9520ea7070c494f23926a0c70193525d8854cc79c875", "generation_seconds_batch": 14.921873726998456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.443574905395508, "genuineness": 4.645420074462891, "identity": 0.18697357177734375, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/cefb01669376124df0e040ad73ab52bb657438e2e5f0be9541f87a715c4e8308.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "8c8cdc83d97ca6b109dd2b235c68b69fea56b482f07e9e74e5776d9f1979254f", "generation_seconds_batch": 16.646911929012276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.300607204437256, "genuineness": 4.406930446624756, "identity": 0.48620617389678955, "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_Shame/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "cfb2f3069c2e789c4a7cf72686c342bda8c8f9d62db18307ba4d117f59a62217", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "54119bcb3b93b3f234332b17818b6dbe783e8f2c8929e7e44b5e8be44e16f9fa", "generation_seconds_batch": 21.9075062579941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.300607204437256, "genuineness": 4.457139015197754, "identity": 0.4691969156265259, "hypothesis": "The 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_Shame/cfb2f3069c2e789c4a7cf72686c342bda8c8f9d62db18307ba4d117f59a62217.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "cfd28d96566e95827b600bf6139cff9c7c7d1000254b624130a77c8bb6535d01", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "626029be95139160da2d4245049c4b2a67232daa3fdbb515042ed47ba207f731", "generation_seconds_batch": 18.171159082092345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.46918290853500366, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/cfd28d96566e95827b600bf6139cff9c7c7d1000254b624130a77c8bb6535d01.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "d039a64a30b7b412d1ec21b105f080e13a153f4077aacb6a1294eb844008a8d0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f37121ba53426ac78c8f84c3cb63758b678bcbfd24ea7ea62b61539ac5e81371", "generation_seconds_batch": 20.065488351974636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 6.316492557525635, "genuineness": 4.143336772918701, "identity": 0.5467163920402527, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d039a64a30b7b412d1ec21b105f080e13a153f4077aacb6a1294eb844008a8d0.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "d04e81f781ee02ab7a9391b7da4405e464609b37742339cc4ee32c8c138a30fd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c309f3aa36d3cd9e5d54502366376891e4c85c61847be8a26b513cf28ed5577", "generation_seconds_batch": 21.636593889910728, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 6.2767791748046875, "genuineness": 4.632867813110352, "identity": 0.4802085757255554, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d04e81f781ee02ab7a9391b7da4405e464609b37742339cc4ee32c8c138a30fd.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "d0886dd9d7a36ebd0cdd41164f6dd0e2164c95493094ecc4dd00da91f1612f39", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7207e6b5a3feae6ec9245e050aafe4be452562432ca821061e5abca3998beef7", "generation_seconds_batch": 20.624459043028764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 5.967014789581299, "genuineness": 4.419482707977295, "identity": 0.5577118396759033, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d0886dd9d7a36ebd0cdd41164f6dd0e2164c95493094ecc4dd00da91f1612f39.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "d08e2dd3e89b27015c9e1549cdd96cb04622121ce5c2abfeb20678f17ad5dc27", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aec86e47074ca424194ac78100e4d709b5d06a0111331f2b8813c237229c27e2", "generation_seconds_batch": 20.580302458023652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.086154937744141, "genuineness": 4.607763767242432, "identity": 0.7134029865264893, "hypothesis": "J'ai trouvé la 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_Shame/d08e2dd3e89b27015c9e1549cdd96cb04622121ce5c2abfeb20678f17ad5dc27.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "d093cd8cfacf99158eb092775c6a6885be206fcc346a5e8e5e00da58a254b809", "bucket": "emo_Shame", "phase": "wording", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "01de3bf727eb6cd73eeba607c3d965d9456012eb0da46d4ad4ecdaf159181f81", "generation_seconds_batch": 17.536916750017554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.662684977054596, "hypothesis": "La porte 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_Shame/d093cd8cfacf99158eb092775c6a6885be206fcc346a5e8e5e00da58a254b809.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "d0dd4faef0a280ccefa58d50c303691f6f3bbddff40339bca235ff479a66b83f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b01f4e4b7fad236e460ed5162e13d08e38b4c4f3722ad8ea562707e08d9de2c3", "generation_seconds_batch": 14.98847919004038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 5.824047088623047, "genuineness": 4.632867813110352, "identity": 0.6607550382614136, "hypothesis": "La porte 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_Shame/d0dd4faef0a280ccefa58d50c303691f6f3bbddff40339bca235ff479a66b83f.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": "d0fcc383fd72dd145fbf753a78d051e1a61473e86aa66eef745ff2a37445b185", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "3b0800e555bc1f0085e0a6db01216cf61af59d533787a64f4b34552774d770f5", "generation_seconds_batch": 14.466073184972629, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06479987502098083, "target_z": -0.27929687255626695, "ce": 5.744620323181152, "genuineness": 4.061748504638672, "identity": 0.4853992164134979, "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_Shame/d0fcc383fd72dd145fbf753a78d051e1a61473e86aa66eef745ff2a37445b185.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "d1012aad3239b97fee56c5b06a6709ad36c10b6cc71da806b7df3395537a6130", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1e4a4cc6bd5e02b8b88c52e4189e60afd21307854a03aa9a69f3965190ffe5a7", "generation_seconds_batch": 22.502233402919956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.300607204437256, "genuineness": 4.193545341491699, "identity": 0.3138827979564667, "hypothesis": "The 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_Shame/d1012aad3239b97fee56c5b06a6709ad36c10b6cc71da806b7df3395537a6130.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "b2d5fd10ba6cc72e5b13a38f43dec52f4cbf982e34cb67287e12373646b3b124", "generation_seconds_batch": 16.70099613198545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.2767791748046875, "genuineness": 3.998987913131714, "identity": 0.4705553650856018, "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_Shame/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "d159ef9eeb1ff8086504ce3ba0ef778059a498c660ec461b95ea8d030d8fd199", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9e85e1cb4e773693fae25ed263d14c52607dc638b1356e34a1614f96d48610e1", "generation_seconds_batch": 19.9494669099804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009914115071296692, "target_z": -0.4218749875591771, "ce": 6.0305562019348145, "genuineness": 4.68307638168335, "identity": 0.5470836162567139, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d159ef9eeb1ff8086504ce3ba0ef778059a498c660ec461b95ea8d030d8fd199.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "d17e76172f18a3a8055e8ffec7de61f236294d03c013c60aa299d1e89fdc98a2", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d8da6684aa68d4af4c39261db2d4a51e0f86e6d4586ae23983f0b428835cd8ad", "generation_seconds_batch": 20.426731970976107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0058201998472213745, "target_z": -0.41406249200232814, "ce": 5.95112943649292, "genuineness": 4.7834930419921875, "identity": 0.6855868101119995, "hypothesis": "La porte 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_Shame/d17e76172f18a3a8055e8ffec7de61f236294d03c013c60aa299d1e89fdc98a2.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "790fd093e7ba8a6866b46be36035b4a47260a639a5c7947e77cb2158d0e42765", "generation_seconds_batch": 14.896239464054815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.292664527893066, "genuineness": 4.193545341491699, "identity": 0.69697505235672, "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_Shame/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "d2840d9cff481dae5f121651ffbaf41b2fce6599b49eadbd55ce103d4500b40f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8385cd2478c877306c58d2be9d7ff052e73c519d37724be0c67dc81c0fd4fa96", "generation_seconds_batch": 21.256263831979595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 6.0146708488464355, "genuineness": 4.356721878051758, "identity": 0.6511786580085754, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d2840d9cff481dae5f121651ffbaf41b2fce6599b49eadbd55ce103d4500b40f.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "d2a38ae570dec5d63fb79de08dbea94a0459d0f7fd767d73bc766bd4636ebdef", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b7fda056093e6a475ed1fdf1ef3293617202ceec4849c77c98e9ffa135bda594", "generation_seconds_batch": 14.890776955056936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05865900218486786, "target_z": -0.29101561589154035, "ce": 6.1020402908325195, "genuineness": 4.6705241203308105, "identity": 0.7778682708740234, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d2a38ae570dec5d63fb79de08dbea94a0459d0f7fd767d73bc766bd4636ebdef.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": "d2b2504a41b16d32fef47f4627f34af1ba555683f8ca1d5b3b0ba70007be331f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f549e522429961baab42e69603e23e02675c9ea3de7b9576f2a523a443f2ae82", "generation_seconds_batch": 23.971455091028474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 5.522225379943848, "genuineness": 4.036643981933594, "identity": 0.7317097187042236, "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_Shame/d2b2504a41b16d32fef47f4627f34af1ba555683f8ca1d5b3b0ba70007be331f.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "d301a0ff9f900b9a3cef0c326f686faed1b05196cee86c4aefaab6215511d8b8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bb5dd136d8cfb42375665acc0b0d40278a7005d48d909a3734a4d3158bf1c996", "generation_seconds_batch": 20.91753686789889, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 5.927301406860352, "genuineness": 4.557555198669434, "identity": 0.4019567668437958, "hypothesis": "La porte 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_Shame/d301a0ff9f900b9a3cef0c326f686faed1b05196cee86c4aefaab6215511d8b8.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "d35099e672ef8ec1f8a641b76283b369e905bcd2903a1e91363f03da3923f1dd", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b5b67c30792c994abda7fe29492b563766c551c3df5485060bd1d67de0b03c76", "generation_seconds_batch": 20.267611159943044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 5.863759994506836, "genuineness": 4.582659721374512, "identity": 0.6080510020256042, "hypothesis": "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_Shame/d35099e672ef8ec1f8a641b76283b369e905bcd2903a1e91363f03da3923f1dd.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "52022e5462aa044f5cfe497f697e4d19a00cb485f6648140571c7c07164c88da", "generation_seconds_batch": 14.88743120606523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.078212261199951, "genuineness": 4.532451152801514, "identity": 0.6472827196121216, "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_Shame/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "d47989a03dfeae832c511bd1624fb021937d61d326f41107d954b0ef65ff9583", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e72d05611fd25aae4232a931034a82fcf0233e9d04004c58a929a5b636386030", "generation_seconds_batch": 22.14649874099996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.006728172302246, "genuineness": 4.231201171875, "identity": 0.44194382429122925, "hypothesis": "De deur staat nog open. Ik heb je ik heb 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_Shame/d47989a03dfeae832c511bd1624fb021937d61d326f41107d954b0ef65ff9583.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "d4afd4dc840c818f32c6f81e27041ead0eeda377138509bea618d8246d8d3daa", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ec883cd77f59bb94895b150aa9aa93ef2577d3c2d73b85c3b0357de105c03453", "generation_seconds_batch": 22.396728722960688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0033911168575286865, "target_z": -0.39648436278133464, "ce": 6.149696350097656, "genuineness": 4.846253395080566, "identity": 0.519811749458313, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d4afd4dc840c818f32c6f81e27041ead0eeda377138509bea618d8246d8d3daa.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "d51216203030a71532a203cd8a1ebe8d592cd94ebe8994bf16b1019c7e47e087", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d20fb16e1e0ebcc65a41d0a3625e27a1c4b0b823c0a3cec93c26fb7e010c0bc9", "generation_seconds_batch": 19.97506153397262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 5.784333229064941, "genuineness": 4.231201171875, "identity": 0.39379337430000305, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d51216203030a71532a203cd8a1ebe8d592cd94ebe8994bf16b1019c7e47e087.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "d56cf4e382c7cb4f2c1ab121d2bc019fcdd429057090cf346ac00f00e1bbe903", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "29e4b9404a4496c5e013217349bb42f69628fb688a58c1f71b413cae1b043432", "generation_seconds_batch": 16.489592397934757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.039595022797584534, "target_z": -0.47851562300058204, "ce": 5.9431867599487305, "genuineness": 4.632867813110352, "identity": 0.7825185060501099, "hypothesis": "La porte 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_Shame/d56cf4e382c7cb4f2c1ab121d2bc019fcdd429057090cf346ac00f00e1bbe903.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": "d58c4dde9702fd70c580d376e98c3e54cfa0e6dbe73f2d1914c00f11d43380cc", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd1a98dbdab7dc08f81839bf5f2532d0971740f08616beee20ecc3f3c3d1aff2", "generation_seconds_batch": 20.232619322952814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.3338901400566101, "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_Shame/d58c4dde9702fd70c580d376e98c3e54cfa0e6dbe73f2d1914c00f11d43380cc.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "d5e70c3447441e7ba70c966040edd6f19998b2df58174453194d983ba4c6a3be", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d65697b16f2c18bc6acd7382678ed8472054a7df1880fbfbd3d4d2b316b37d7c", "generation_seconds_batch": 24.673413568059914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.133810997009277, "genuineness": 4.469690799713135, "identity": 0.493857204914093, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude ruim. 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_Shame/d5e70c3447441e7ba70c966040edd6f19998b2df58174453194d983ba4c6a3be.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "d61d18a56ec0a59ba9693b38bdeee3266431e314acdb4b96510ae9c0a4370491", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3ae1ca060a4c4860b68770371fa4ebc3937a5e905f2b2848d1c52911b9c32840", "generation_seconds_batch": 16.030965421930887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.689021587371826, "genuineness": 4.570107460021973, "identity": 0.6409890651702881, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d61d18a56ec0a59ba9693b38bdeee3266431e314acdb4b96510ae9c0a4370491.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": "d675eb043f7338929c9202ce16ca9efd22317f600335011704f2e10afa622cc7", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "084ac2911e6aba0d58845d16696e4ec63975608dd02cbe88f78fa5ea097d2730", "generation_seconds_batch": 21.880211566924118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 5.855817794799805, "genuineness": 4.507347106933594, "identity": 0.6115789413452148, "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_Shame/d675eb043f7338929c9202ce16ca9efd22317f600335011704f2e10afa622cc7.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": "d706562f4a650664628d90a6e1c22e0a9a5e66cdfe4539b8644bd2f213b2046e", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a4e93ec9b98d820db544fb069b8b29506779ef7c7bab70747a7575043a2346b", "generation_seconds_batch": 20.2623477979796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 5.784333229064941, "genuineness": 4.250029563903809, "identity": 0.538703978061676, "hypothesis": "La carretera irá a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d706562f4a650664628d90a6e1c22e0a9a5e66cdfe4539b8644bd2f213b2046e.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "d7094e3a168f3ca8ae5a6dcded17161856c1e8efe134c31318458ca2a35426ae", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bc5db24a2b103b57e64246cc82b22aa1bbf927dc0d46551255fedd821303b784", "generation_seconds_batch": 20.30699260206893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.054384231567383, "genuineness": 4.6705241203308105, "identity": 0.7135070562362671, "hypothesis": "La porte 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_Shame/d7094e3a168f3ca8ae5a6dcded17161856c1e8efe134c31318458ca2a35426ae.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": "d7c278015c11f4135172fb7a539a517aa6de293ef0b5e4e63d8c87f3dfb4ee04", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "6a6c6828d4d0ce09d2f91f92a4b3fe4923f5100dc20846339c0815757d597743", "generation_seconds_batch": 17.591208588914014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08526946604251862, "target_z": -0.24023436633585546, "ce": 6.165581703186035, "genuineness": 4.570107460021973, "identity": 0.7946799993515015, "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_Shame/d7c278015c11f4135172fb7a539a517aa6de293ef0b5e4e63d8c87f3dfb4ee04.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": "d7d331b3608d492daf896e5c89c0a5b870f2d4cc0babbf2e30d2ddf082bb0edd", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f691c9f5da6b1ab46ed0c186adddefaa1e814f7acad88a04ede479167f4ca60", "generation_seconds_batch": 20.661907093017362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.661221981048584, "genuineness": 4.457139015197754, "identity": 0.7424156665802002, "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_Shame/d7d331b3608d492daf896e5c89c0a5b870f2d4cc0babbf2e30d2ddf082bb0edd.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "d7ee194f3c2635eac974d2280b966428e22189e468029a56eac53a6fe187f43a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dd7af505f28dd2e38d443df1590beb75cffb121c8939c99d4c022f5658b2b483", "generation_seconds_batch": 20.441806128947064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 5.919358730316162, "genuineness": 4.375550270080566, "identity": 0.5270466804504395, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d7ee194f3c2635eac974d2280b966428e22189e468029a56eac53a6fe187f43a.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "d8dfd377dd27703e64be9d69775bfb047163d68765967a113978f50a741812f0", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "14a68038d3130657daa5b43f4af2a820a15fbcbbf210065e79f12c8926bd930c", "generation_seconds_batch": 22.181434343918227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 5.80021858215332, "genuineness": 4.6203155517578125, "identity": 0.6399121284484863, "hypothesis": "J'ai trouvé la 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_Shame/d8dfd377dd27703e64be9d69775bfb047163d68765967a113978f50a741812f0.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": "d96d43af84143b02aa103ce49f6268ed9504c578b64bc2229cd5308de43b3110", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "ac236a54a5710c34066af7087b835985f339725b9ba66c3e478742bfd1dfb56d", "generation_seconds_batch": 14.5197204380529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042283326387405396, "target_z": -0.3222656265551029, "ce": 5.6413655281066895, "genuineness": 4.15588903427124, "identity": 0.6949965953826904, "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_Shame/d96d43af84143b02aa103ce49f6268ed9504c578b64bc2229cd5308de43b3110.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "d9a4df9aa1f6ded6a777a513c1af53d9858e49c40dfbbac79d88589999b6f7d7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9068aa43e28cf7f1d4239f56061261ca77d0a01d79282706db901d964dc77f81", "generation_seconds_batch": 22.25768242694903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06889379024505615, "target_z": -0.27148437699941796, "ce": 5.967014789581299, "genuineness": 4.595211505889893, "identity": 0.7253855466842651, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/d9a4df9aa1f6ded6a777a513c1af53d9858e49c40dfbbac79d88589999b6f7d7.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "da0d486b3054fe9a487f3605d3d3f4d8f27a71bb1556dfd0e6b1232f15e3f7fe", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b5ec69b3dd3557aa50345f1247f54ca2d95f2874e55947790e0effeb36937658", "generation_seconds_batch": 22.18106907804031, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 5.673136234283447, "genuineness": 4.6956281661987305, "identity": 0.6883598566055298, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/da0d486b3054fe9a487f3605d3d3f4d8f27a71bb1556dfd0e6b1232f15e3f7fe.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": "da4d168314cfad27e73c2565aa40d2b6d11d84f0203ce93c57a548924a17ad02", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96a582f3d5285d8c9c6d0805f50f3b266e8e58bcab2420c9b1d9f8fe22817f97", "generation_seconds_batch": 17.29400595696643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 5.506340026855469, "genuineness": 3.911123275756836, "identity": 0.00901797879487276, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek hindelen. En daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/da4d168314cfad27e73c2565aa40d2b6d11d84f0203ce93c57a548924a17ad02.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "da7fb3f65038327d0f9d1e4bbfc25c6d0735a8d6383a364b5c49b96ccf70f04f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "beb0e223c7a32757078f17a852e087dad2015717fd1e617835d30cfb322bc79b", "generation_seconds_batch": 23.061181511962786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042283326387405396, "target_z": -0.3222656265551029, "ce": 5.5659098625183105, "genuineness": 4.6203155517578125, "identity": 0.660271167755127, "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_Shame/da7fb3f65038327d0f9d1e4bbfc25c6d0735a8d6383a364b5c49b96ccf70f04f.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "4271364fda735b1883b911505ce0cef84151caed08f8efd0b3895598ed66c22c", "generation_seconds_batch": 15.082718699006364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.4515180587768555, "genuineness": 4.080576419830322, "identity": 0.413377046585083, "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_Shame/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.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": "dbc0532bd96752a27993308cacd25a03d112f972b25022304fc577ac19c8c88a", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab04a2faf457e4e57c7521cf8aedfbf8de02d93e1f7552abfc2a331b616a886e", "generation_seconds_batch": 24.140351698966697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.09409761428833, "genuineness": 4.457139015197754, "identity": 0.6245591044425964, "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_Shame/dbc0532bd96752a27993308cacd25a03d112f972b25022304fc577ac19c8c88a.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "dc1622d2329ce0efdc1d8d6fa2c9cd97140666c86a3ff563be00751011928ba4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "be36097af0b34401397ebe8facdb4a98f5af18b5e22249d985f872c874d50f13", "generation_seconds_batch": 20.019999742042273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010937601327896118, "target_z": -0.42382812566647265, "ce": 6.006728172302246, "genuineness": 4.883909225463867, "identity": 0.7582294940948486, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/dc1622d2329ce0efdc1d8d6fa2c9cd97140666c86a3ff563be00751011928ba4.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "dc3dfb6486c08ba076769f1ade823b2300fbedea6e9dfb179aa5ef48f24a9f29", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "db3f88e17fca0893c90a907c6d0356a30c14f0c2a995e4a4100d76bf6a8cafd9", "generation_seconds_batch": 20.203011045930907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.149696350097656, "genuineness": 4.494794845581055, "identity": 0.568968653678894, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/dc3dfb6486c08ba076769f1ade823b2300fbedea6e9dfb179aa5ef48f24a9f29.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "dcb5faa29a99ea533b5b799ec1811db815100a6dac926613bc52a2e524fea2d4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c91e06626490d55dfa8dfd808b133bc4abab1dd8f1363100a9d9a91dbf1c4990", "generation_seconds_batch": 23.757029858999886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.042283326387405396, "target_z": -0.3222656265551029, "ce": 6.141753673553467, "genuineness": 4.362998008728027, "identity": 0.4540744721889496, "hypothesis": "Ik ik heb het kleine doosje gevonden. Het stond naast het oude graam. 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_Shame/dcb5faa29a99ea533b5b799ec1811db815100a6dac926613bc52a2e524fea2d4.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "dd2ff5681d89e47b53a2b990be9b072425e0ce5c20bb68fc87912527896e9930", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5e6c11749127fdce4a280fb6bd6e330259d27fe085eee799f13e45475f9090e1", "generation_seconds_batch": 16.634623192017898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.268836498260498, "genuineness": 4.6705241203308105, "identity": 0.7616934776306152, "hypothesis": "La porte 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_Shame/dd2ff5681d89e47b53a2b990be9b072425e0ce5c20bb68fc87912527896e9930.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "dd62bfd1d30450c1e193dc7c0338c85cd4154eed6ad80859591b26ce1a53864a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5e1405fa2ff5b98ae635d7a4aa7050b4b0c51f22e95f4dd19957902850c6731f", "generation_seconds_batch": 23.109273437061347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044330283999443054, "target_z": -0.31835937877667836, "ce": 6.078212261199951, "genuineness": 4.356721878051758, "identity": 0.4821048378944397, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/dd62bfd1d30450c1e193dc7c0338c85cd4154eed6ad80859591b26ce1a53864a.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "ddbfe0bf8070ca5c2f05ea59650849a2f8b4c06d8244c2aba64080361cc75489", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b5b378d806b603cd1757e9bfd5abdd7323284b75cd42118d189b74ff2e55b9c1", "generation_seconds_batch": 24.236359754926525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 5.879645347595215, "genuineness": 4.3504462242126465, "identity": 0.13481014966964722, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ddbfe0bf8070ca5c2f05ea59650849a2f8b4c06d8244c2aba64080361cc75489.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": "ddc4a63def15c32f31afec11348b13ae3090044729be2db34e178100363f2b6d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fb294580cc8e6ff19c791d7d3cfcbf63dd6ce0434cdb7d64efea55ad60645628", "generation_seconds_batch": 14.474077310995199, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 6.213237762451172, "genuineness": 4.055472373962402, "identity": 0.15997035801410675, "hypothesis": "De sleutels liggen op de keukentafel. Ikek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ddc4a63def15c32f31afec11348b13ae3090044729be2db34e178100363f2b6d.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "de119b5d95f3ff4f4732cd7486dbf359f6409b2c3c912118ca75004b7453b91a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5daffcd40a97490fb193ab61109446cf2e5be65c0b0c1194f6d695d50dc0fb99", "generation_seconds_batch": 20.144304884015583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 5.855817794799805, "genuineness": 4.607763767242432, "identity": 0.8217567205429077, "hypothesis": "J'ai trouvé la 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_Shame/de119b5d95f3ff4f4732cd7486dbf359f6409b2c3c912118ca75004b7453b91a.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": "de6f4649164f15035c056530b437e6d982f10630c6f838f69d78a0a57cd4605f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "1f9cb2aadc76b307dba7f1d1556a008a522d84209abc03ac6a95ff9bdb0b3f8f", "generation_seconds_batch": 14.5197204380529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 5.593709468841553, "genuineness": 4.111956596374512, "identity": 0.7962759733200073, "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_Shame/de6f4649164f15035c056530b437e6d982f10630c6f838f69d78a0a57cd4605f.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": "deed3923530153d5324c22b7e2fc921eeb56369ebc12008e0d4ea730bd23f339", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "588a51103e43963f4f83b48f343b78520d8583678b0f0ec86b17029eea11e0b5", "generation_seconds_batch": 24.312210104078986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 5.959072113037109, "genuineness": 4.607763767242432, "identity": 0.7857879400253296, "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_Shame/deed3923530153d5324c22b7e2fc921eeb56369ebc12008e0d4ea730bd23f339.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "df7b9f76f87c528375fcd37ccde998cb472ce1647c0b0dac826690aa86a807d5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce10748c4e2119f545daa91096c4d7de8d76cd1262749e8392126a2f32c23248", "generation_seconds_batch": 15.133816722081974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011961087584495544, "target_z": -0.42578126377376824, "ce": 6.292664527893066, "genuineness": 4.256305694580078, "identity": 0.48008641600608826, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/df7b9f76f87c528375fcd37ccde998cb472ce1647c0b0dac826690aa86a807d5.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "e0014e031816525998109ca48c9ce8f8c9bb944d4a5f1945659cc2252427fc69", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bbb66318335a995754b191a186a10bf40d4dad982f1395d8b9ac5b1d80ffd78b", "generation_seconds_batch": 14.83345873793587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05047115683555603, "target_z": -0.30664063544140496, "ce": 5.442798614501953, "genuineness": 4.519899368286133, "identity": 0.6984742879867554, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e0014e031816525998109ca48c9ce8f8c9bb944d4a5f1945659cc2252427fc69.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": "e0b8a601c005d6ae5882e6cd05da08198c7602a884e87093557193648411ae81", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8301c70a224ded40bbd11de7d6b7bde8480d11d7286efddf95755945f23f75fd", "generation_seconds_batch": 16.035451264004223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 5.808161735534668, "genuineness": 4.532451152801514, "identity": 0.879846453666687, "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_Shame/e0b8a601c005d6ae5882e6cd05da08198c7602a884e87093557193648411ae81.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": "e0c1de5cddcc20786a200c84f6d260c5a52e167dc8140e669e8383630c6911cd", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "b8fef3bbde1d821f3c40e66bd59fc93d78a59196aa7ced390b3afd966f90d8a9", "generation_seconds_batch": 15.469032479915768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07503466308116913, "target_z": -0.2597656336641445, "ce": 5.919358730316162, "genuineness": 4.281409740447998, "identity": 0.6108418703079224, "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_Shame/e0c1de5cddcc20786a200c84f6d260c5a52e167dc8140e669e8383630c6911cd.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": "e0c7b24ca111ef304191c792d47d604a600a95070699d94d906d492582f0a9b6", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5472e9a4ec2736dae384ccbc5035d321e97c4dbf24c63a1bf41a1ed6899ce27d", "generation_seconds_batch": 15.011670393054374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 5.959072113037109, "genuineness": 4.099404335021973, "identity": 0.5192896127700806, "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_Shame/e0c7b24ca111ef304191c792d47d604a600a95070699d94d906d492582f0a9b6.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "e0cdb28e061e02ae7eb132852de57418ff105d30f3418473954a2bbb1efde267", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1f4e52cc6c7b9e8629074e491335a975c11671bfc014fbb34213a5409e442d18", "generation_seconds_batch": 15.916080081020482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 5.129063129425049, "genuineness": 3.9550557136535645, "identity": 0.29834848642349243, "hypothesis": "Daar staat 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_Shame/e0cdb28e061e02ae7eb132852de57418ff105d30f3418473954a2bbb1efde267.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "e0e2dec3a1b742d9a06f387515b5f3cd5e76333e5d9be5eb4ed1334d21eea716", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "449d096bcfd6d6ee8835cef16a7dd22d81396260864b6b9da3560d0fcd712862", "generation_seconds_batch": 23.01182540995069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 6.109982967376709, "genuineness": 4.808597087860107, "identity": 0.754123866558075, "hypothesis": "La porte 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_Shame/e0e2dec3a1b742d9a06f387515b5f3cd5e76333e5d9be5eb4ed1334d21eea716.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "e176ff5b9b4c30a92333e5bb8a7043fae3a39cfa3bdb4eee155e97d86fcf71ef", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0eb6fc224cff4a1c62c0c414071e1e57f8eb5e6789c7bee01fc9a52710d07f6c", "generation_seconds_batch": 15.584855855093338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007485032081604004, "target_z": -0.38867186722448566, "ce": 5.796247482299805, "genuineness": 4.306513786315918, "identity": 0.33007264137268066, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e176ff5b9b4c30a92333e5bb8a7043fae3a39cfa3bdb4eee155e97d86fcf71ef.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "e1af515800911c3a2f6dcf9aa1e05f29c94219d2fa6307e4e7e7aa4f40698f35", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3c1332bae25eca150ac1bc8e7e1d07d52d36e69ac95baeaf457cb1a37da58840", "generation_seconds_batch": 22.72839836694766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.5539960861206055, "genuineness": 4.607763767242432, "identity": 0.5999306440353394, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e1af515800911c3a2f6dcf9aa1e05f29c94219d2fa6307e4e7e7aa4f40698f35.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "e1eb7181037c9668ff3760e59ab7d6947be66bf1ed573e30eb7cf4af5d2b5f35", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e2353d11640aec90b0334f6058320281cdc991c1655b2e597910ed6189c29a1d", "generation_seconds_batch": 20.09122965403367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 5.895530700683594, "genuineness": 4.68307638168335, "identity": 0.8281398415565491, "hypothesis": "La porte 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_Shame/e1eb7181037c9668ff3760e59ab7d6947be66bf1ed573e30eb7cf4af5d2b5f35.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "e23494d999ac5161783a66b1baca82200977f4c161404e870423f3c964543207", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b2efa8006960ee9e40de96fdb685a63527efb7f914dcc63a7bf31a60e71d241b", "generation_seconds_batch": 17.663883102010004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0007028132677078247, "target_z": -0.4042968867743503, "ce": 5.661221981048584, "genuineness": 4.6705241203308105, "identity": 0.7475311756134033, "hypothesis": "La porte 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_Shame/e23494d999ac5161783a66b1baca82200977f4c161404e870423f3c964543207.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "e235fd712abe1cbb9b404e769014e48cd153bb76bc1da955b23a031644492a15", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8fe4530722cab90cbe5beddecdeb896904fbc071041fbf1db27a359cf6e2500a", "generation_seconds_batch": 22.66008185001556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 6.070269584655762, "genuineness": 4.607763767242432, "identity": 0.6297168731689453, "hypothesis": "La porte 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_Shame/e235fd712abe1cbb9b404e769014e48cd153bb76bc1da955b23a031644492a15.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "e23e15365ba0f4521cbfc8739bc3e6729c2772fefd5605266d63e3eeaf3e045c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5421e21bedf2e67f40846d787fae874778d8a774763fd43b11bef220411a4c5b", "generation_seconds_batch": 19.97471984801814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04023636877536774, "target_z": -0.32617187433352735, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.6959296464920044, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e23e15365ba0f4521cbfc8739bc3e6729c2772fefd5605266d63e3eeaf3e045c.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "e250cdc167c0421fcbbc62e35046a8588a385d6d5ded9784ccdbcc3404141f54", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c84b5266cfa39541ab2450ff5211427504016ed6c4a1aeaa0205448fdd37e8e5", "generation_seconds_batch": 20.391907381941564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.0146708488464355, "genuineness": 4.7081804275512695, "identity": 0.8096952438354492, "hypothesis": "La porte 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_Shame/e250cdc167c0421fcbbc62e35046a8588a385d6d5ded9784ccdbcc3404141f54.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "e26443be445dbcc6d9afde9cb07a12d2554f3979589e74dc46b22e1b819d1e7b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4b57331d44471b1002047896f63c2cd0d66ea0d4fe2efa258bf5fad0d903016e", "generation_seconds_batch": 20.73968642600812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 5.708878040313721, "genuineness": 4.645420074462891, "identity": 0.722896158695221, "hypothesis": "J'ai trouvé la 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_Shame/e26443be445dbcc6d9afde9cb07a12d2554f3979589e74dc46b22e1b819d1e7b.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "e297a3d924afffe171b4534fc42d829b6cb48ffca70e93426fc76a069967a792", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0d46ae5e830148fa0403f29b821d152ec71eda30eb27af5dcf5747aed72e4478", "generation_seconds_batch": 20.145564800011925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 5.863759994506836, "genuineness": 3.9048471450805664, "identity": 0.35428255796432495, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e297a3d924afffe171b4534fc42d829b6cb48ffca70e93426fc76a069967a792.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": "e2aaa19856ea2f23051d426e06038d3bdb29e73240dcc57f5cb13ffe033bc436", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "465910f984e22985aa769dcd51541294924ca2d3bb1c4f5617678e2893112ff2", "generation_seconds_batch": 20.05306732398458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01567286252975464, "target_z": -0.37304687611078774, "ce": 6.022613525390625, "genuineness": 4.168440818786621, "identity": 0.6979748010635376, "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_Shame/e2aaa19856ea2f23051d426e06038d3bdb29e73240dcc57f5cb13ffe033bc436.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "e2afadca4a1dc47cbea329223ce81c6dbb83a8651d11ae0a57320704465b918a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8e39f939c7b4dae2de2d283ac36a42f9254a420fc15f0a94edef97808e221bcf", "generation_seconds_batch": 22.66008185001556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 5.959072113037109, "genuineness": 4.65797233581543, "identity": 0.6337203979492188, "hypothesis": "La porte 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_Shame/e2afadca4a1dc47cbea329223ce81c6dbb83a8651d11ae0a57320704465b918a.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "e2d1fb1c5176667cb1e29079e527684a90a30d778a2fad22a9454a95bc6f3478", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "41138a1baed643272287a346235d6d5f31ef7a4e61cf655912d805fba25455b7", "generation_seconds_batch": 20.151643987046555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.292664527893066, "genuineness": 4.6203155517578125, "identity": 0.5819829702377319, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e2d1fb1c5176667cb1e29079e527684a90a30d778a2fad22a9454a95bc6f3478.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "e309df020c889f937220a1f23d99cc996e2369125d924ba5a47427fd303d270f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "49125da6cb8dee50579ef7d8524c855441369750a3eb6048a32a9af8ffe15cfb", "generation_seconds_batch": 16.179308263002895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.395919322967529, "genuineness": 4.3127899169921875, "identity": 0.572772741317749, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e309df020c889f937220a1f23d99cc996e2369125d924ba5a47427fd303d270f.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": "e3e0ea61a2514985ae7ff0302fdf4864117c03534088d9e605fcf95c84ec9e69", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d58523cb193c0cf270987953571aaf3538db82839b5b89eaaffe98040076ccfe", "generation_seconds_batch": 20.661907093017362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 5.736677646636963, "genuineness": 4.20609712600708, "identity": 0.650915801525116, "hypothesis": "J'écris le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e3e0ea61a2514985ae7ff0302fdf4864117c03534088d9e605fcf95c84ec9e69.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "e436e7e22c061121ac63228ed1fb0d3bef656a2b66980d6fd10e57d8a6616c26", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "56a37166a2e8a395df9232efb9a2c94a366211ab5d947700ceb29468ad60b17a", "generation_seconds_batch": 20.01746664592065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.017078474164009094, "target_z": -0.4355468690017461, "ce": 6.38003396987915, "genuineness": 4.68307638168335, "identity": 0.5283371210098267, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e436e7e22c061121ac63228ed1fb0d3bef656a2b66980d6fd10e57d8a6616c26.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "e50f4e857449967b9a0a8b3f7ee2b131ecfe0bfc76a28122e0e94450033aa21e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "650764a985c2a038e6546831d32e6560f09db626c7788b7e140a0b009f0df35f", "generation_seconds_batch": 20.393773288931698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 5.696964263916016, "genuineness": 4.883909225463867, "identity": 0.7588526010513306, "hypothesis": "La porte 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_Shame/e50f4e857449967b9a0a8b3f7ee2b131ecfe0bfc76a28122e0e94450033aa21e.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "e53ad9d563170e3f3c5f698b5987f3495010ef9a545a9f303c7b347c857a046d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1f28eb345a41b1e18e01f6531a42a124991727644b3f3c84176bdf1e25848190", "generation_seconds_batch": 20.950545059051365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 6.324435234069824, "genuineness": 4.457139015197754, "identity": 0.44376733899116516, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e53ad9d563170e3f3c5f698b5987f3495010ef9a545a9f303c7b347c857a046d.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "e5521ca9fea51766373b3ddd5767cc8c0dd9ae5acf73a0df584abff60f5de938", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8544a9795b4c32a8c4dcc6faca82cad4a8fdb451650a8f9d93eab4c0633ab1fb", "generation_seconds_batch": 14.921873726998456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004796728491783142, "target_z": -0.4121093823311992, "ce": 6.181467056274414, "genuineness": 4.582659721374512, "identity": 0.45585930347442627, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e5521ca9fea51766373b3ddd5767cc8c0dd9ae5acf73a0df584abff60f5de938.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "e5c19719f46bd7c9db8b5870db0e788ccafc9c84c228b6f4b26ebd69f76f3b3d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "99bba3da211792d10401ba34b8f724c8110a9db4b6cd892fa3b181e080793916", "generation_seconds_batch": 20.488657042966224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 5.879645347595215, "genuineness": 4.7458367347717285, "identity": 0.637538492679596, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e5c19719f46bd7c9db8b5870db0e788ccafc9c84c228b6f4b26ebd69f76f3b3d.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "e5db6e204c0515bd5b82ef6318d4283693c15aa25cd4eab3b6b536e54ad9cfd9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ddef0e91a6f89fc58a6bb057bf9653012cbecd6392d697bdd40c436cf4f6c8fe", "generation_seconds_batch": 21.726405469933525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06172943115234375, "target_z": -0.285156258441987, "ce": 5.967014789581299, "genuineness": 4.65797233581543, "identity": 0.20026502013206482, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit.", "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_Shame/e5db6e204c0515bd5b82ef6318d4283693c15aa25cd4eab3b6b536e54ad9cfd9.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "e68343284b766332f09a137b22a4ecddc1d7a03b54e2aaad8f538a68693ff430", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "018ee8d23b7ffc960e6f46e5a490304987d2dc540374105ea86759736599ff8b", "generation_seconds_batch": 20.952861405094154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.23706579208374, "genuineness": 4.871357440948486, "identity": 0.7087435126304626, "hypothesis": "J'ai trouvé la 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_Shame/e68343284b766332f09a137b22a4ecddc1d7a03b54e2aaad8f538a68693ff430.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "61b5d4a928a7c634a861b209b0ca315764b93efdb099936ba6405649547c4035", "generation_seconds_batch": 15.616806780919433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.41180419921875, "genuineness": 4.394378662109375, "identity": 0.42620646953582764, "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_Shame/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "e6f2133936d3e1dc082559e369f41b1fbfd386eb9b69153903a2a9dab90f1194", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3928025b37cca94d53ff31d6fd969866ea8ee22e28f554901cbbcef868cfb083", "generation_seconds_batch": 14.835922288009897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.300607204437256, "genuineness": 4.7332844734191895, "identity": 0.7035541534423828, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e6f2133936d3e1dc082559e369f41b1fbfd386eb9b69153903a2a9dab90f1194.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": "e71bf6ce04aa730586b5adcfa4a38295b0be9baaced49f0ebc41a046af3ac4ff", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "9e0055b6ba22b4a279d27aa695e837446525512d58ec4ff302c5d025df199204", "generation_seconds_batch": 18.003607311984524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 5.911416053771973, "genuineness": 4.231201171875, "identity": 0.5857188701629639, "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_Shame/e71bf6ce04aa730586b5adcfa4a38295b0be9baaced49f0ebc41a046af3ac4ff.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "e72503c853ea63cebd4f45469306621abfa391f383d7ac3097e59f70d0f87964", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8bbbe5d17fd7e880f7891acb1289168bdf543f44730fa4c021f0c80c24ba1a51", "generation_seconds_batch": 17.454277896904387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04740072786808014, "target_z": -0.3124999928909583, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.66443932056427, "hypothesis": "De deur staat nog open. Ik heb je jassen 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_Shame/e72503c853ea63cebd4f45469306621abfa391f383d7ac3097e59f70d0f87964.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "e82c6ee91dc8792d795db5c40f6e202db28d9096adf7b80316126d8d52d63263", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1bf431c6d04dbb6c9d8b066e48eccddfd975774fbfb373ef5c34ab272b10ee2d", "generation_seconds_batch": 20.411190609098412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 6.109982967376709, "genuineness": 4.833701133728027, "identity": 0.6677517890930176, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e82c6ee91dc8792d795db5c40f6e202db28d9096adf7b80316126d8d52d63263.mp3" }, { "id": "emo_Shame-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-0", "key": "e8bf944e0821510697dbfaf72fee859afd36f93536f0a8ed626da62f8cdfabca", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De deur staat nog open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6898397930537212de9e7f290896bd371d5d7ea00ce1e4a83c80dcad2c4b4be6", "generation_seconds_batch": 19.986415499006398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 6.006728172302246, "genuineness": 4.444586753845215, "identity": 0.566365659236908, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/e8bf944e0821510697dbfaf72fee859afd36f93536f0a8ed626da62f8cdfabca.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": "e8d19bbd1218e0a01d9dd8bee3d5993f333591203e2b2c673deb1a3f8d0b460d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ec25c239d8c9b745cb50144e71ba0fea01e2c3ff629007c6cf7b2602233c467", "generation_seconds_batch": 14.610216099070385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07503466308116913, "target_z": -0.2597656336641445, "ce": 5.831989288330078, "genuineness": 4.250029563903809, "identity": 0.6514458656311035, "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_Shame/e8d19bbd1218e0a01d9dd8bee3d5993f333591203e2b2c673deb1a3f8d0b460d.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": "e96a9ecb8d00376e0cd43275da02c221978d0b7d44347a9a8226351240b1392e", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "b18f1c520e7d7da24ef265637727bdca009966e4a9baa5c05f4ec70bd026389c", "generation_seconds_batch": 15.798909601056948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.229123115539551, "genuineness": 4.256305694580078, "identity": 0.42248207330703735, "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_Shame/e96a9ecb8d00376e0cd43275da02c221978d0b7d44347a9a8226351240b1392e.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": "e98f40295d8744a7f274396da92255a640a411462c39ec28ed7ce89f0f791c8f", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1f9db0d8e2185725523dc6f1c1039229ea0b6d4ab0372624f1d8e8e6baf131a", "generation_seconds_batch": 21.370640140026808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030001580715179443, "target_z": -0.3457031132256497, "ce": 6.3641486167907715, "genuineness": 4.6203155517578125, "identity": 0.4974941909313202, "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_Shame/e98f40295d8744a7f274396da92255a640a411462c39ec28ed7ce89f0f791c8f.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "5834fa5c4ae805c09bddaa4bc239da60613e15f3017740882eb63ef06ecdbcae", "generation_seconds_batch": 16.646911929012276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.324435234069824, "genuineness": 4.7332844734191895, "identity": 0.45631974935531616, "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_Shame/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.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": "ea6ee44a91d8eebe1157ff67264e63442b82ad3db007b62d1ddf377b8f7ba769", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff12bb7f329e80f1425312c1379f6157d6a5bbe86e29173131915eb624a9a916", "generation_seconds_batch": 24.06663585198112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 5.967014789581299, "genuineness": 4.821148872375488, "identity": 0.6358867287635803, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ea6ee44a91d8eebe1157ff67264e63442b82ad3db007b62d1ddf377b8f7ba769.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": "eab14acb8f077376ba7c04849228a792da0f2b9e836bf19e1a0ab22cba2b3164", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "45a6a585500085069ba7f7a45c3f3b372121b59a0ec4e542f51cc15b2ba141c8", "generation_seconds_batch": 17.268023142940365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.197352409362793, "genuineness": 4.419482707977295, "identity": 0.7061407566070557, "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_Shame/eab14acb8f077376ba7c04849228a792da0f2b9e836bf19e1a0ab22cba2b3164.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "eaf8c09d5129e7e4553fd06b82d5261acc3e4007fc9bee5778fd907292531108", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a63b9566062ea8900389863e37938afa2cb06aff9939b4db3fefb135b52fb4f6", "generation_seconds_batch": 17.828152089030482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05047115683555603, "target_z": -0.30664063544140496, "ce": 5.593709468841553, "genuineness": 4.6956281661987305, "identity": 0.6052284240722656, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/eaf8c09d5129e7e4553fd06b82d5261acc3e4007fc9bee5778fd907292531108.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "eb62685f80e5e5604dd668f46e874894a13778b220ead8844784f884e1b45a7d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fa5a6f7c41ebcf1db73067ea048cbe150ad6b2a207dfe3e9d447b4281d99f541", "generation_seconds_batch": 20.33373983099591, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 5.260117053985596, "genuineness": 4.381826400756836, "identity": 0.6530106067657471, "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_Shame/eb62685f80e5e5604dd668f46e874894a13778b220ead8844784f884e1b45a7d.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "ebd01aa759ded1fddb0df9bc8a0924b22472cbb3b475b2c9862562cc93b29675", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5780c5daeb43782da9aa3c187daeba2ddbba6ed51a51903d70341e9d2435cb00", "generation_seconds_batch": 25.341422375990078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 5.6254801750183105, "genuineness": 4.469690799713135, "identity": 0.6177170872688293, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ebd01aa759ded1fddb0df9bc8a0924b22472cbb3b475b2c9862562cc93b29675.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "32080ec221273283df040c479048a8f528f84640faf11ee4c988fb0110b4ac5c", "generation_seconds_batch": 14.939674741937779, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.205295085906982, "genuineness": 4.250029563903809, "identity": 0.8872846364974976, "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_Shame/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.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": "ec1c072c0aed685b12d2c241ef8148f61e5b533c32afc03a9223014913f5728a", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "436bd4cd406b0ca341b70d9152d4c9f4aadc77e3639e0b6bca15b2f3283f513e", "generation_seconds_batch": 14.529730711015873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06787031888961792, "target_z": -0.2734374866705469, "ce": 5.704906940460205, "genuineness": 4.482243061065674, "identity": 0.6398465037345886, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ec1c072c0aed685b12d2c241ef8148f61e5b533c32afc03a9223014913f5728a.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": "ec6b44335f955be1b16dde66969e09dcacd62a6d28b38ab24af6a7bbea376a55", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0138db0c6f2696fceca3467d74613261bce7a6ddd11c51bd88c528ca4564289d", "generation_seconds_batch": 21.880211566924118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 5.736677646636963, "genuineness": 4.432034492492676, "identity": 0.7058430910110474, "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_Shame/ec6b44335f955be1b16dde66969e09dcacd62a6d28b38ab24af6a7bbea376a55.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "ecebb5180708aa59efec953a5867020c49352ba7775ad6171aeb9e74a923c5b2", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "167d4130b9d1b5ca374293b525eb013b014fbbdf261f1341a335f8b79993d46b", "generation_seconds_batch": 20.041249466012232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.6413655281066895, "genuineness": 4.720732688903809, "identity": 0.8017352819442749, "hypothesis": "La porte 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_Shame/ecebb5180708aa59efec953a5867020c49352ba7775ad6171aeb9e74a923c5b2.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": "ecee911b42d7f18402611f812531f90f14422ebcc0778a913415dac5a2fdf3f0", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51a39dcd8c7bfe294408a4d25800999bf3269a2f325322ce5c2ea99b11056c6e", "generation_seconds_batch": 20.2623477979796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 5.804190158843994, "genuineness": 4.162164688110352, "identity": 0.4801137149333954, "hypothesis": "Una carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ecee911b42d7f18402611f812531f90f14422ebcc0778a913415dac5a2fdf3f0.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": "ed51e425b61d11e6b9a7c429fc251cd75592dce9b248eea037aaffbb00a0b930", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "262694b7f33a0b6f7fd4d8572f3747ac7d2212489a38d57d30cebf6286476c71", "generation_seconds_batch": 21.042331198928878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06787031888961792, "target_z": -0.2734374866705469, "ce": 5.816103935241699, "genuineness": 4.582659721374512, "identity": 0.7632753252983093, "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_Shame/ed51e425b61d11e6b9a7c429fc251cd75592dce9b248eea037aaffbb00a0b930.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "ed5fa379c48995cc10495392c4853ad9d28d13a45d360ae30d034825e3bf8c62", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "76a944e407947bb10a1ca4a114d7f1be9f4ff65b964dbdbb9a655ae7f09b0367", "generation_seconds_batch": 20.128002773970366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04535377025604248, "target_z": -0.31640624066938283, "ce": 6.38797664642334, "genuineness": 4.362998008728027, "identity": 0.7661087512969971, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ed5fa379c48995cc10495392c4853ad9d28d13a45d360ae30d034825e3bf8c62.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "ee0c63ae75ec5bb731280c22033b4503859c49327fb32b3e494d4aed67ffb12d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4edadc2e018d6555280199d810ea960f25e49b385ab6987c9db4d76c814f5b55", "generation_seconds_batch": 21.05250572890509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.8267837762832642, "hypothesis": "La porte 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_Shame/ee0c63ae75ec5bb731280c22033b4503859c49327fb32b3e494d4aed67ffb12d.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "ee226d0946d5cc2e463ec23cb4015092c4d2771fec52fa1f163d0d079a16842f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f834369dde2d38caec874076069dbecca737d9abcfd59787f90eba26e1bb145a", "generation_seconds_batch": 22.560060454066843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.292664527893066, "genuineness": 4.3881025314331055, "identity": 0.4558560252189636, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ee226d0946d5cc2e463ec23cb4015092c4d2771fec52fa1f163d0d079a16842f.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "ee3034b06b47d47851e12250c47c81268dff7b765ea986e2711ad6e79d541e56", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "13b061015babb2ce86dd7499ed4f002e550cc472677cc5d9601072f337d515f4", "generation_seconds_batch": 20.73585873900447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 5.637393951416016, "genuineness": 4.632867813110352, "identity": 0.7842488288879395, "hypothesis": "La porte 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_Shame/ee3034b06b47d47851e12250c47c81268dff7b765ea986e2711ad6e79d541e56.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "ee4256d53bd14653d69686b6cdea7f2090ba3addc2e1abfd275a068716d59fa4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a6f1a1ff8194ab94ad39d7f9941e2729ca754bcf75b327eddd99b5a152249ad6", "generation_seconds_batch": 21.16260478296317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.911416053771973, "genuineness": 4.532451152801514, "identity": 0.7332367300987244, "hypothesis": "J'ai trouvé la 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_Shame/ee4256d53bd14653d69686b6cdea7f2090ba3addc2e1abfd275a068716d59fa4.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "ee69f7e3534c440fecf9f81d4d94bf769197ac1a35250db5b60ceecd975e6104", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7eaf569d3ced360c90f8d00ed7f563d8f0f0a7b95f36b398a1ac516d815b672b", "generation_seconds_batch": 19.799478401895612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.125868320465088, "genuineness": 3.9048471450805664, "identity": 0.2294243723154068, "hypothesis": "The 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_Shame/ee69f7e3534c440fecf9f81d4d94bf769197ac1a35250db5b60ceecd975e6104.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "eeaa46def0a63096731f93cbfa98a3ef38c2babdcc3a6ed2257300b57d8e8e7e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2e98ff07421fe766f205488083b2a41cacdb12457a8f300fcb14ecb3122b8840", "generation_seconds_batch": 20.783395397942513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.7071487903594971, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/eeaa46def0a63096731f93cbfa98a3ef38c2babdcc3a6ed2257300b57d8e8e7e.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "ef0f8708fb68c863bac61b88ee840aa93b0d61de8512d16e82f1209bca9d39f5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "df89608bb3464e5e309d579e8fd0d621fb0f1eee144b097e450543aa70e101ec", "generation_seconds_batch": 21.05250572890509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 6.1020402908325195, "genuineness": 4.770940780639648, "identity": 0.709726095199585, "hypothesis": "La porte 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_Shame/ef0f8708fb68c863bac61b88ee840aa93b0d61de8512d16e82f1209bca9d39f5.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": "efa8ade274f85edad6751cb80ee46c3e7d962a92d14bcca19a5d5209671e2805", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c353b05f7eed1ff676e9057085c2a2102e6964a9c8c4f0a9c670e3916fb927ae", "generation_seconds_batch": 24.06663585198112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 5.855817794799805, "genuineness": 4.369274139404297, "identity": 0.6990906000137329, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/efa8ade274f85edad6751cb80ee46c3e7d962a92d14bcca19a5d5209671e2805.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "f08a4154304ed9d6e0b330722ef950fc05ab3cee119d54f7dde109c75c48d43b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "045890452d81c375a5cc0cd181a8cb4b6430f41cf7e44c8155b8ecc2edb3b3d6", "generation_seconds_batch": 20.521867661038414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06275291740894318, "target_z": -0.2832031203346914, "ce": 5.792276382446289, "genuineness": 4.482243061065674, "identity": 0.8300254940986633, "hypothesis": "J'ai trouvé la 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_Shame/f08a4154304ed9d6e0b330722ef950fc05ab3cee119d54f7dde109c75c48d43b.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "f0bd07b90a303a2b083965d9c170bd5fecc6ecbd994cd14d406262b0dd2ba8d8", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d571c3dc83ae8b0d892a85bea6909d0d48314cbe7bc6f9d5a286d33fba7487ac", "generation_seconds_batch": 20.24525788403116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.252951145172119, "genuineness": 4.406930446624756, "identity": 0.40089279413223267, "hypothesis": "The 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_Shame/f0bd07b90a303a2b083965d9c170bd5fecc6ecbd994cd14d406262b0dd2ba8d8.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": "f1466f6a588549eeae53761a651598d4eb0bc8f0e1a6d8813ad89e4ee0546202", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "ff75dd3cd8d5231933a588d44ac79ab9e7c1486eec6dd635297b32cee2f81a5f", "generation_seconds_batch": 14.466325231012888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044330283999443054, "target_z": -0.31835937877667836, "ce": 5.7406487464904785, "genuineness": 4.005263805389404, "identity": 0.09900619089603424, "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_Shame/f1466f6a588549eeae53761a651598d4eb0bc8f0e1a6d8813ad89e4ee0546202.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "f1eb1af578290cd8810f66940b576f318ee6f2a3f66002a11906f08f4eb88a6e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c1d51149963a9ae95e9de3e37ce0176b906acfe92b595b9bc6aa30d7774ec90a", "generation_seconds_batch": 20.21930895606056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053541600704193115, "target_z": -0.3007812495556849, "ce": 6.070269584655762, "genuineness": 4.607763767242432, "identity": 0.492740273475647, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f1eb1af578290cd8810f66940b576f318ee6f2a3f66002a11906f08f4eb88a6e.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "f4e37f83c12b2e738f1410e22eab5d0e63dc464eb2e20bbcabc6cd714afdd29b", "generation_seconds_batch": 15.011497945990413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.7358145117759705, "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_Shame/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "f248767ed1665c12b1f050ef5b01731dc4f3e9323fca20beef6c96b256f6b3f4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7ecafb718e4f00ed0b22be938665c7ba1981a99c3e50fca2444fd82858646250", "generation_seconds_batch": 20.30117319501005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03511896729469299, "target_z": -0.33593750799767186, "ce": 6.157639026641846, "genuineness": 4.68307638168335, "identity": 0.7500521540641785, "hypothesis": "J'ai trouvé la 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_Shame/f248767ed1665c12b1f050ef5b01731dc4f3e9323fca20beef6c96b256f6b3f4.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "f2d33614a3628f22ec4079eba05fa152a06fb33ff9b25884ad6037758f0f3692", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "624ad79d45f0ef3c6729979df59fa797c5add5053f522edeb8c5f957d0449d03", "generation_seconds_batch": 20.30117319501005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 6.062326908111572, "genuineness": 4.896461486816406, "identity": 0.8351953029632568, "hypothesis": "J'ai trouvé la 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_Shame/f2d33614a3628f22ec4079eba05fa152a06fb33ff9b25884ad6037758f0f3692.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "f2d580910542690541006522da102f15eb87d31b84ee8f5d142c61edd3417aad", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e3a480e81d8c0ded4515679901f645dcd018868d5e09017f37bf9e6ab8834ce8", "generation_seconds_batch": 22.40669416298624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 5.7128496170043945, "genuineness": 4.432034492492676, "identity": 0.5020765066146851, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f2d580910542690541006522da102f15eb87d31b84ee8f5d142c61edd3417aad.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "f2ea3157bf14f3834fa4b9ff7921709fac0a8623397fab504bfa7e798d21015c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "515f766c2d12ef3e70d03b5f9a33c3c594f6fd7ea9593c39aab4b6070f1f7742", "generation_seconds_batch": 20.85800313600339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.022613525390625, "genuineness": 4.6705241203308105, "identity": 0.6604024171829224, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f2ea3157bf14f3834fa4b9ff7921709fac0a8623397fab504bfa7e798d21015c.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "f2f1048cbcf09f20098b68446b57180e6b5b0520dbd73673713c81a6852bd011", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "90d230528def85e4da458c8d7cd3482a58cca3e6e569d81027528ab371287ef1", "generation_seconds_batch": 20.903288008994423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00032067298889160156, "target_z": -0.4023437486670547, "ce": 5.990842819213867, "genuineness": 4.833701133728027, "identity": 0.7299567461013794, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f2f1048cbcf09f20098b68446b57180e6b5b0520dbd73673713c81a6852bd011.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "f34aeb30d0c956554a99a0e8c1fcf999c9c00a49335bc0141fe7888d22f4c892", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "817e46c5698efbb2ce4117419b17dd16ae283ff1443feb8458713bcd53087d7f", "generation_seconds_batch": 23.709746224922128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 6.133810997009277, "genuineness": 4.720732688903809, "identity": 0.49949318170547485, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f34aeb30d0c956554a99a0e8c1fcf999c9c00a49335bc0141fe7888d22f4c892.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "f3c743f5ab6caffc22301eb46fdb16ccc6d46ea249abb6b68ab33948dbc252ba", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9593d6b281450846e28514b8d3b1d9e17be43cb72737999904bac717b5150e32", "generation_seconds_batch": 20.75440801505465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 5.927301406860352, "genuineness": 4.293961524963379, "identity": 0.5441994667053223, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f3c743f5ab6caffc22301eb46fdb16ccc6d46ea249abb6b68ab33948dbc252ba.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "f42fe4348cf3cc603b2c13a0c8c8a6402f4a4f76c51a0ac949c51f98f5608ece", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6fda06f0067a7c404203aa764ffb8ffe2f48897a5b8c16f298886a21d212a42e", "generation_seconds_batch": 14.721013586968184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 5.736677646636963, "genuineness": 4.570107460021973, "identity": 0.519396185874939, "hypothesis": "La porte 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_Shame/f42fe4348cf3cc603b2c13a0c8c8a6402f4a4f76c51a0ac949c51f98f5608ece.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "f45a29813aa283d103be34d779ae6d712b6a7ed437462191e029b08cfc612609", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "21489dab86ffe7c3fb96376b926f7a452ca5e17954a2453df40e388b070b3dd5", "generation_seconds_batch": 20.544169612927362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.0305562019348145, "genuineness": 4.6705241203308105, "identity": 0.7175225019454956, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f45a29813aa283d103be34d779ae6d712b6a7ed437462191e029b08cfc612609.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "f4a3e544fb7d76d8e8b20f6b5f19a60c595f8fb40deb4c7ece1a6b0acce3e509", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e40b1fa89ff2bd1225356cebf0c54863f8b242e5d10f37b3d8c72b484d544f6", "generation_seconds_batch": 20.76856239303015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 5.669164657592773, "genuineness": 4.507347106933594, "identity": 0.5719941854476929, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f4a3e544fb7d76d8e8b20f6b5f19a60c595f8fb40deb4c7ece1a6b0acce3e509.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "f4bef73c4882ee69ee87827224c8615d235dee813fb5e5a1674717d3180f2cf4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "83f46b1fdaa5180e7337f9b047456f8a5dbab8b1c9f59174470c149afd2d65a9", "generation_seconds_batch": 16.188317687017843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456508696079254, "target_z": -0.29882811144838933, "ce": 5.839932441711426, "genuineness": 4.7081804275512695, "identity": 0.5693054795265198, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f4bef73c4882ee69ee87827224c8615d235dee813fb5e5a1674717d3180f2cf4.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "f5086690ee27285ea7ec455662e60ff6c60860701f7a3a05e399cb2a9b8b280f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d2588fdf7d9941135d511b5324a40e24f8faf47c9dbea180ac8034d5524d51fb", "generation_seconds_batch": 20.783395397942513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.165581703186035, "genuineness": 4.557555198669434, "identity": 0.7520164847373962, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f5086690ee27285ea7ec455662e60ff6c60860701f7a3a05e399cb2a9b8b280f.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "f53a15776bfd11e80d67002c7408ba04c035cb63e56e6c5dcc50843b5864e8b7", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3490c5afa0957d117df31c68873e4c946fe8e326a21727c6ac892ecb87c130bd", "generation_seconds_batch": 19.947585616027936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006461545825004578, "target_z": -0.39062500533178124, "ce": 6.038498878479004, "genuineness": 4.645420074462891, "identity": 0.6711138486862183, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f53a15776bfd11e80d67002c7408ba04c035cb63e56e6c5dcc50843b5864e8b7.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "f540591d9227828ebcc59f19a7abf944b7e979d0b03d9305746ab93350259e1f", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fa9eb3324764a7c092511771092f45376a4496c494ed98e83d00f7ed54e2e213", "generation_seconds_batch": 16.980711470008828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.006728172302246, "genuineness": 4.256305694580078, "identity": 0.24758127331733704, "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_Shame/f540591d9227828ebcc59f19a7abf944b7e979d0b03d9305746ab93350259e1f.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "f57f96574fb5818985beaba8ed8b27e396a492c116383ae2cd84fb770a3ffdd2", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ed16c758595a3c8b55eec21d7a2dd858ab52ed387d0b09c07492e289898cfac2", "generation_seconds_batch": 15.131971598952077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 6.292664527893066, "genuineness": 4.457139015197754, "identity": 0.6132029294967651, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f57f96574fb5818985beaba8ed8b27e396a492c116383ae2cd84fb770a3ffdd2.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": "f5ba4ad4f2f30bf05461f19d2ae89ebddcbb6c125a04c365a3f5ce668ce59b9b", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "57ba3403d2db7f78fc8c22d9aaeea26dde848820744a47dd02f120eb95fe29be", "generation_seconds_batch": 14.710835366975516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0494476854801178, "target_z": -0.30859374511253385, "ce": 5.974957466125488, "genuineness": 4.532451152801514, "identity": 0.7810180187225342, "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_Shame/f5ba4ad4f2f30bf05461f19d2ae89ebddcbb6c125a04c365a3f5ce668ce59b9b.mp3" }, { "id": "emo_Shame-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-nl-1", "key": "f61225da57909f02ad86c9fbb12ebc47ed6b4d4df9639332797fc37019dd8574", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4a4c4c2a86a7ed908f4d1271223d77c255b99be95f2f278d8a37e35fd2c4a32b", "generation_seconds_batch": 23.555159265059046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.165581703186035, "genuineness": 4.3881025314331055, "identity": 0.5519272089004517, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f61225da57909f02ad86c9fbb12ebc47ed6b4d4df9639332797fc37019dd8574.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": "f66612a765d871adc0d778a4b11c320b63a0acfe7035e14c67369dd732ada8a7", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "87cd0e378a16d765b0bfb6d3715b0ff45d4a2edc9d52241a629f85191a477deb", "generation_seconds_batch": 14.571717766928487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019125431776046753, "target_z": -0.43945311678017057, "ce": 5.95112943649292, "genuineness": 4.143336772918701, "identity": 0.541336715221405, "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_Shame/f66612a765d871adc0d778a4b11c320b63a0acfe7035e14c67369dd732ada8a7.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "f72813ea06db19537394cfc5f9485c66b52fd04321164d32f20a9649744acea4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ee77389d94a3bee10a4d72e4490b3e936cf4a480a81d462b4167fe510d775697", "generation_seconds_batch": 21.35962164599914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.053541600704193115, "target_z": -0.3007812495556849, "ce": 6.340320587158203, "genuineness": 4.632867813110352, "identity": 0.7333166003227234, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f72813ea06db19537394cfc5f9485c66b52fd04321164d32f20a9649744acea4.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "f764d6258a01168e85dfe0c0a99f1ee68714ec6ac050ce0e260167c292dd7235", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c27016b806d92acc2d3e19990a07b00beec37fbbee9062787fc1400989e25c8b", "generation_seconds_batch": 23.169508755905554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.157639026641846, "genuineness": 4.570107460021973, "identity": 0.48750802874565125, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f764d6258a01168e85dfe0c0a99f1ee68714ec6ac050ce0e260167c292dd7235.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "bcb8fbc699cfe6c5a1403b3a5c331b34a4d4b91b722bcc85f34a7ded089f4f21", "generation_seconds_batch": 15.024872343987226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.086154937744141, "genuineness": 4.494794845581055, "identity": 0.5749041438102722, "hypothesis": "Les clés are sur la table de la cuisine. J'ai regardé dans le tiroir, 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_Shame/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "f80ff5ee65b2505bf7f084829cdce327a8e8836081457dc55a9bbe27df46905e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb59688a1f4291f4c788b1b5a2a295d72a25fe03cc4412280c437c24fce4c5a5", "generation_seconds_batch": 16.21274096297566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 6.09409761428833, "genuineness": 4.7332844734191895, "identity": 0.425784170627594, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f80ff5ee65b2505bf7f084829cdce327a8e8836081457dc55a9bbe27df46905e.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "f83576bab4e0af85b35005f98e33d7ae4b65f818f00c5f9469a7de60a6b80ce4", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "30c03fe56fc23138b02eb68d5f312b96f3ee540614b3676439ccb8daaf0929db", "generation_seconds_batch": 23.3943360990379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.284721851348877, "genuineness": 4.632867813110352, "identity": 0.4777752459049225, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f83576bab4e0af85b35005f98e33d7ae4b65f818f00c5f9469a7de60a6b80ce4.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_Shame", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": "af0ca66dff9d588b6560317e653f83d563d67e32a6c1522595afd59966f7d47d", "generation_seconds_batch": 15.993559505906887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027954623103141785, "target_z": -0.3496093610040742, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.6070138216018677, "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_Shame/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "f8e2158983f6a64137f353cf8b5f006732005607a752ba2f1b946b9bd1a24708", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ae932626e93ebad291c2be1f30b88c4b9e9c8a52bd72f34e25dd6b1d4240c906", "generation_seconds_batch": 20.092638136004098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07196423411369324, "target_z": -0.2656249911136979, "ce": 6.046441555023193, "genuineness": 4.519899368286133, "identity": 0.596372127532959, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/f8e2158983f6a64137f353cf8b5f006732005607a752ba2f1b946b9bd1a24708.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "fa100f135867a8af3e8c9c9b7a264c0b8270654e931d8f9d4a4db2058df62eac", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f1104d44b7e2238b5e3a1a2fabdcd5e8b05d286bda8ee64bc32267f379fba85c", "generation_seconds_batch": 16.634623192017898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.141753673553467, "genuineness": 4.256305694580078, "identity": 0.7712932229042053, "hypothesis": "La porte 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_Shame/fa100f135867a8af3e8c9c9b7a264c0b8270654e931d8f9d4a4db2058df62eac.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "fae49a8070a0841fd905af1eddbadaf3c16e5f602c71f1220e8c417784e9e3c5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1f36e397ba1a9ebf1d01d98d5c009b606a9c6002d57e0084d250c4d95223b4a5", "generation_seconds_batch": 22.114438630989753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.046441555023193, "genuineness": 4.105680465698242, "identity": 0.47975486516952515, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fae49a8070a0841fd905af1eddbadaf3c16e5f602c71f1220e8c417784e9e3c5.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "fb9aa20a5fcf0763c8b35f231563ad93639f409ec85a94d4aa8bc1cce96ba97a", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cfc78e9e54ff30b219e8a741fbeab6effb13a02b28011045cbd0f083872b67f2", "generation_seconds_batch": 22.66996895405464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.205295085906982, "genuineness": 4.758388519287109, "identity": 0.6642570495605469, "hypothesis": "J'ai trouvé la 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_Shame/fb9aa20a5fcf0763c8b35f231563ad93639f409ec85a94d4aa8bc1cce96ba97a.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": "fbdeac775012235734e101b287f7a558c5c44d99882851a38f3946c53289f33c", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e207956d89672ebb7171267ce8204cf8d770ca4dfd75d221da87d885f43a1cd", "generation_seconds_batch": 22.20848460996058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03716592490673065, "target_z": -0.3320312602192474, "ce": 5.903473377227783, "genuineness": 4.268857479095459, "identity": 0.520542562007904, "hypothesis": "The keys are on the kitchen table. I checked the drawer, and then looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fbdeac775012235734e101b287f7a558c5c44d99882851a38f3946c53289f33c.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "fc038d883dda3274ae431ac1370281a5d372055b2d78633237b1704ee10d6e35", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ae87a50f8d210f093276f3793ab98f68d60617c025d710c87a90d21da27f6d01", "generation_seconds_batch": 19.971593913040124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.055588558316230774, "target_z": -0.2968750017772604, "ce": 6.006728172302246, "genuineness": 4.758388519287109, "identity": 0.5300235748291016, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fc038d883dda3274ae431ac1370281a5d372055b2d78633237b1704ee10d6e35.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "fc2c9ee4e3248911ad1ece84a9245b7b1bcceae0112d9a191277957c5328f56c", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aee6cfc53c38a9ac5815c755e7c5d76c2e288bb6b9dcc81ad5157c425a036fe2", "generation_seconds_batch": 14.840334779000841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 5.911416053771973, "genuineness": 4.582659721374512, "identity": 0.6711692214012146, "hypothesis": "J'ai trouvé la 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_Shame/fc2c9ee4e3248911ad1ece84a9245b7b1bcceae0112d9a191277957c5328f56c.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "fc528d398dd3e6154b350ffd1400f4a316c7036cc0498a69b5f260305d6bd50b", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b56d06902961d91cc5f25a05e6685057416a0715ed743ff399b521c4da924e24", "generation_seconds_batch": 20.38845843600575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.252951145172119, "genuineness": 4.532451152801514, "identity": 0.38954177498817444, "hypothesis": "The 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_Shame/fc528d398dd3e6154b350ffd1400f4a316c7036cc0498a69b5f260305d6bd50b.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": "fc54d606d2dd4fe5ba21d8481dde6bf50a53e32aa044ab781c602321d1edaf8d", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "9d0409eddb0aecdb0872d10035d7a0223d30f21307cc5eb4bcb1db416d4bc2b6", "generation_seconds_batch": 14.72734099603258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06070595979690552, "target_z": -0.2871093681131159, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.6308161020278931, "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_Shame/fc54d606d2dd4fe5ba21d8481dde6bf50a53e32aa044ab781c602321d1edaf8d.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": "fc86be8b420fac468d311bcb42fd86e241e017cdcf91f1b62d482de15b2caca4", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [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": "16e76d605d4410c3451a0a6926185c9c9db5092564f1c4f19e2eff626f27cda3", "generation_seconds_batch": 14.783872278989293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.173524379730225, "genuineness": 4.168440818786621, "identity": 0.4299584627151489, "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_Shame/fc86be8b420fac468d311bcb42fd86e241e017cdcf91f1b62d482de15b2caca4.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "fcbae025218aa81ff8348ae64070bedfa0c4af075e6195540713d4d4c1e4b33d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e1c232c6faa8056624d607913516c75c01441505633d046f662e5a0a4012933a", "generation_seconds_batch": 20.0596611360088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05251811444759369, "target_z": -0.30273438766298044, "ce": 5.752562999725342, "genuineness": 4.532451152801514, "identity": 0.5193381905555725, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fcbae025218aa81ff8348ae64070bedfa0c4af075e6195540713d4d4c1e4b33d.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "fcbd1dc58129f84f34cbc8a679c667c2a632d8808a5ad97745b49829cd0a2dee", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3744501ed9e241efafcd0971010616024042367acd016e4204e14d9c2839bffa", "generation_seconds_batch": 20.903288008994423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.6645335555076599, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fcbd1dc58129f84f34cbc8a679c667c2a632d8808a5ad97745b49829cd0a2dee.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "fce8f9439edf0e84de0f5cc8b2571ad37a3e3179dd425cbfb97945ca10078252", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "603af5e8b8372f49f43655e0ee06d8227021eb425403f9b45ff6063a2c543ea2", "generation_seconds_batch": 19.92382470902521, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.173524379730225, "genuineness": 4.6705241203308105, "identity": 0.7146085500717163, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fce8f9439edf0e84de0f5cc8b2571ad37a3e3179dd425cbfb97945ca10078252.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "fcf011e8b9f583edc862591a245bae6209b3e574f0b99e13f46051a26d765493", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e27b8eaf2e810a4304d93f29f0c3f8db0f6850d30e6f0c53eb0c58efaa449790", "generation_seconds_batch": 20.951461654971354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 6.165581703186035, "genuineness": 4.243753433227539, "identity": 0.28621333837509155, "hypothesis": "The 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_Shame/fcf011e8b9f583edc862591a245bae6209b3e574f0b99e13f46051a26d765493.mp3" }, { "id": "emo_Shame-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-1", "key": "fd5fb5dd9f4839e9fa2d49c7e3db22712c0922ad3e01476b5ea5a510fd87f98e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "38156fea163a82c30934465048c169375284491395df80f2e4d2233527c4d443", "generation_seconds_batch": 20.274696117034182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0017262846231460571, "target_z": -0.40624999644547916, "ce": 5.982900142669678, "genuineness": 4.369274139404297, "identity": 0.744102954864502, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fd5fb5dd9f4839e9fa2d49c7e3db22712c0922ad3e01476b5ea5a510fd87f98e.mp3" }, { "id": "emo_Shame-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-0", "key": "fe6559c1c711504008e18463ea554934932f95ad3a071ea1ba0448409dbef044", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cd4293996a247783ae62db9287fec0c017fda9f101274ae23ff1e6d9c222cd92", "generation_seconds_batch": 20.391907381941564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.0305562019348145, "genuineness": 4.582659721374512, "identity": 0.7560467720031738, "hypothesis": "La porte 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_Shame/fe6559c1c711504008e18463ea554934932f95ad3a071ea1ba0448409dbef044.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "fe6a2565cbe772ca79c05a62601312e78a810e4145f1ec2fc64143449d0816d9", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "37ee99bc7d32f685b4d0ede033db7775c9601f233241b914fbff169d098055d6", "generation_seconds_batch": 20.59681755292695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06377638876438141, "target_z": -0.2812500106635625, "ce": 6.157639026641846, "genuineness": 4.821148872375488, "identity": 0.7028590440750122, "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_Shame/fe6a2565cbe772ca79c05a62601312e78a810e4145f1ec2fc64143449d0816d9.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "fe7fb0244cb9282c5cae3f164f63c815b5275e0a857dba00f9203fffb9ae6f35", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f5b805086a13cd38ab116301ac5c8655b1d23466c726438871e774a1ee4e4aa9", "generation_seconds_batch": 20.01746664592065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019125431776046753, "target_z": -0.43945311678017057, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.41064977645874023, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fe7fb0244cb9282c5cae3f164f63c815b5275e0a857dba00f9203fffb9ae6f35.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "feb3d90468afa76988493bda3103dff8d3621fe67fd04f9c7280235ebcac44f5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "660ce30b6ba225653baa62a1ef70283dddae559cb9071eaa99054da112b1a715", "generation_seconds_batch": 21.436078867060132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06275291740894318, "target_z": -0.2832031203346914, "ce": 5.967014789581299, "genuineness": 4.607763767242432, "identity": 0.6086087822914124, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/feb3d90468afa76988493bda3103dff8d3621fe67fd04f9c7280235ebcac44f5.mp3" }, { "id": "emo_Shame-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-0", "key": "fede2383de1319f11fe2b69bb432d2fdf82750d9e76c84812a529b4d59c4ed70", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5c92365cf265f539d3535382cc4de26325acfcb7a763b3e51beaab2a19708224", "generation_seconds_batch": 15.757384749944322, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03921288251876831, "target_z": -0.3281250124408229, "ce": 5.903473377227783, "genuineness": 4.68307638168335, "identity": 0.6041113138198853, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/fede2383de1319f11fe2b69bb432d2fdf82750d9e76c84812a529b4d59c4ed70.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": "ff0b0166fbbfe5a2776768757b33ffdf71bf386c2b96988368d96d20482e75d0", "bucket": "emo_Shame", "phase": "heldout", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "007fa19eae41fa061e13406ebd06fe49f3e9c1e784d98adb471c7fbcccd3ae3f", "generation_seconds_batch": 21.264940754976124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 5.804190158843994, "genuineness": 4.281409740447998, "identity": 0.5509899854660034, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und umprüfe 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_Shame/ff0b0166fbbfe5a2776768757b33ffdf71bf386c2b96988368d96d20482e75d0.mp3" }, { "id": "emo_Shame-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-es-0", "key": "ff5f6ce66beac6ff4ccb3ed625bcd84979c00260f3b85d6f9192672e12cc6053", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bcfbd36119a2da57d66629d4b298cc18c400ced2208229ab68eb5a8024fe7d55", "generation_seconds_batch": 21.46534316893667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 5.7128496170043945, "genuineness": 4.482243061065674, "identity": 0.3715321123600006, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ff5f6ce66beac6ff4ccb3ed625bcd84979c00260f3b85d6f9192672e12cc6053.mp3" }, { "id": "emo_Shame-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-de-1", "key": "ff96370de57c56407d38952f07260f1e35008023845e18a39de9b9ffa7add10d", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "169bbbbd1c6f402a69884f12c1f9c1a5164101f52c741649ce25a8a404120b82", "generation_seconds_batch": 20.545681989984587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010555461049079895, "target_z": -0.3828125097749323, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.6786158084869385, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ff96370de57c56407d38952f07260f1e35008023845e18a39de9b9ffa7add10d.mp3" }, { "id": "emo_Shame-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-fr-1", "key": "ffd364f16ce6fea0dfeed4fa774f02922c04e0ef88859f8075833525ee0d892e", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "70daa91aa0f1f749c3e10b74225e0d508a6f5b37284c67d2800ca6942939771c", "generation_seconds_batch": 20.429618560010567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 5.998785495758057, "genuineness": 4.808597087860107, "identity": 0.723819375038147, "hypothesis": "J'ai trouvé la 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_Shame/ffd364f16ce6fea0dfeed4fa774f02922c04e0ef88859f8075833525ee0d892e.mp3" }, { "id": "emo_Shame-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-1", "key": "ffd89ab31efbb119d722aeeff29e3bd76384cf96883d7916095b996d5bdbbab5", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] I found the little box.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d45324401e8f2e1107867e6d93e43cd735addd85f9ac6eb367376b6ceac98a5c", "generation_seconds_batch": 20.546278005000204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 6.332377910614014, "genuineness": 4.419482707977295, "identity": 0.28130364418029785, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Shame/ffd89ab31efbb119d722aeeff29e3bd76384cf96883d7916095b996d5bdbbab5.mp3" }, { "id": "emo_Shame-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Shame-en-0", "key": "ffee4245ea2a4b659d75ce18fcc1340151c575e03c99103739d160ce05cc5704", "bucket": "emo_Shame", "phase": "grid", "candidate": "manual-48b6c1c43c18", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Treat the vocal tract as constricted; the shame manifests as a physical tightening around the mouth and throat.\nSCRIPT:\n(Begin with a constricted resonance, as if the vocal cords are physically strained before speaking.) [3.2 seconds duration] The door is still open.\n(Maintain a very tight, pressurized quality throughout, preventing any natural vocal release or expansion.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp intake of breath that punctuates the silence immediately after the final utterance.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f4f474a3f2e78a99475f4ac2e4ebac9d18d3d99c728ff9092e0745bb6c46bac1", "generation_seconds_batch": 15.652800529962406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.09409761428833, "genuineness": 4.419482707977295, "identity": 0.5179361701011658, "hypothesis": "The 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_Shame/ffee4245ea2a4b659d75ce18fcc1340151c575e03c99103739d160ce05cc5704.mp3" }, { "key": "original-emo_Shame-de-0-seed1701-scale0.0", "bucket": "emo_Shame", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "3ce2404c48624794471009710a332d6c8033f46973b5d40c0a5feecca3a9ff23", "task_id": "emo_Shame-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.197352409362793, "genuineness": 4.406930446624756, "identity": 0.38141733407974243, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/5594eeceea9a91cd60372082.mp3" }, { "key": "original-emo_Shame-de-0-seed1701-scale0.5", "bucket": "emo_Shame", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "81b5d26f564fc5682a52ba07b52b8acb3a00579a2776cff0987dbdbca3548f25", "task_id": "emo_Shame-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.053541600704193115, "target_z": -0.3007812495556849, "ce": 6.324435234069824, "genuineness": 4.582659721374512, "identity": 0.5820983648300171, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/f6ed92c2cb71ce3fe5741a0b.mp3" }, { "key": "original-emo_Shame-de-0-seed1701-scale0.75", "bucket": "emo_Shame", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "5b0eea8c91ec4c3a2c5b17305c34ea7b28ec3088fa6b121e5e2560270557e3e9", "task_id": "emo_Shame-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.05763551592826843, "target_z": -0.29296875399883593, "ce": 6.23706579208374, "genuineness": 4.645420074462891, "identity": 0.5834676027297974, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/85f3a8d2258276ac3f1c47fa.mp3" }, { "key": "original-emo_Shame-de-0-seed1701-scale1.0", "bucket": "emo_Shame", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "9a8e4f03253bd0ed8ba43bf86cd8191e081b9a78e8f6356a28965a096f734bd7", "task_id": "emo_Shame-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.05149464309215546, "target_z": -0.3046874973341094, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.6148910522460938, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/d01bdd7a5541d5e288107744.mp3" }, { "key": "original-emo_Shame-de-0-seed1702-scale0.0", "bucket": "emo_Shame", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "5bfad63eb658858d754eed990110c7c1e178089a2de08b48f849433dc8589d21", "task_id": "emo_Shame-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.03818941116333008, "target_z": -0.3300781221119518, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.5566220283508301, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/160405df61418f4c946473c7.mp3" }, { "key": "original-emo_Shame-de-0-seed1702-scale0.5", "bucket": "emo_Shame", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "c820fdc2f821d54eb2aef436e5b37d6c7a207b6f25d2a9e0729e27bd47903f5c", "task_id": "emo_Shame-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.05968247354030609, "target_z": -0.28906250622041146, "ce": 6.141753673553467, "genuineness": 4.218649387359619, "identity": 0.658585786819458, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/63b0d693fbc48e15957e2ca9.mp3" }, { "key": "original-emo_Shame-de-0-seed1702-scale0.75", "bucket": "emo_Shame", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "b5d88d6192314fbb13daf6205c19e2e221bf81fdc14be6d182abd0db24280e41", "task_id": "emo_Shame-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.0566120445728302, "target_z": -0.29492186366996487, "ce": 6.221180438995361, "genuineness": 4.406930446624756, "identity": 0.3289604187011719, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/af0506bbc1773972a7b9a7bd.mp3" }, { "key": "original-emo_Shame-de-0-seed1702-scale1.0", "bucket": "emo_Shame", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "1e2c738af724f30ba5c6b84c72b3b8ce0c35eccd1182e66c3affdfd609763a33", "task_id": "emo_Shame-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.055588558316230774, "target_z": -0.2968750017772604, "ce": 6.1894097328186035, "genuineness": 4.570107460021973, "identity": 0.5593855381011963, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/0b34dad91ebb772f629dd241.mp3" }, { "key": "original-emo_Shame-de-1-seed1701-scale0.0", "bucket": "emo_Shame", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "b9accb087b41cc9ee3cdd5271c2d4727656f122b19d95bde5ab7c148a1403e4d", "task_id": "emo_Shame-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.372091293334961, "genuineness": 4.287685871124268, "identity": 0.4805188775062561, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/b3bbb38c8b2cb7d17e720121.mp3" }, { "key": "original-emo_Shame-de-1-seed1701-scale0.5", "bucket": "emo_Shame", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "8b46d667fe8d534e65059d3661b658d6223a5a6fc9679c4d4e4154b31db6a011", "task_id": "emo_Shame-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 6.435632705688477, "genuineness": 4.494794845581055, "identity": 0.5134610533714294, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/ba291a2b4045638f2609d483.mp3" }, { "key": "original-emo_Shame-de-1-seed1701-scale0.75", "bucket": "emo_Shame", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "95df8156f34d84e9319a4055d3e0e2f3ef4bd306b6c61ebbfd9b0e621258b28a", "task_id": "emo_Shame-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.017719820141792297, "target_z": -0.3691406283323633, "ce": 6.41180419921875, "genuineness": 4.143336772918701, "identity": 0.5989855527877808, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/c563c9fab6de1aa38da3052c.mp3" }, { "key": "original-emo_Shame-de-1-seed1701-scale1.0", "bucket": "emo_Shame", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "76cb40d401fd38ad3a1a694e14507bc349e5430b72e5d1e9a2e4b69d35ce9402", "task_id": "emo_Shame-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.031025052070617676, "target_z": -0.34375000355452084, "ce": 6.419747352600098, "genuineness": 4.331617832183838, "identity": 0.6332280039787292, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/36eb121ce49d29b6845bfe6f.mp3" }, { "key": "original-emo_Shame-de-1-seed1702-scale0.0", "bucket": "emo_Shame", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "d04a4a02f02014af844048f568fa0a70b8a592e44ab5ede48d1fe5ef0774d902", "task_id": "emo_Shame-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.324435234069824, "genuineness": 4.268857479095459, "identity": 0.5237773656845093, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/ca30057e3d000cdde8c2eabf.mp3" }, { "key": "original-emo_Shame-de-1-seed1702-scale0.5", "bucket": "emo_Shame", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "2c6e1fe1b79ce682a038d3b42bfbaf1f5c72cf4f8e3036606bceeb01f0ad2dbd", "task_id": "emo_Shame-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.01362590491771698, "target_z": -0.37695312388921226, "ce": 6.475345611572266, "genuineness": 4.331617832183838, "identity": 0.3878786563873291, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/54d56b88deecdabb0df18ed9.mp3" }, { "key": "original-emo_Shame-de-1-seed1702-scale0.75", "bucket": "emo_Shame", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "fb62360aeb743b8a725b78fc11e535c0a65abb00b6ab17fc768195fffc6088bd", "task_id": "emo_Shame-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.356205940246582, "genuineness": 4.281409740447998, "identity": 0.5469740033149719, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/99c84b7213216647106d504c.mp3" }, { "key": "original-emo_Shame-de-1-seed1702-scale1.0", "bucket": "emo_Shame", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "cf8ef2c6da5d7028370f5e160342fbf486eeb4524c4325e00ae254f5bfa3116b", "task_id": "emo_Shame-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.348263263702393, "genuineness": 4.287685871124268, "identity": 0.5350914597511292, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/de/31dea1af199667f46b6e19b7.mp3" }, { "key": "original-emo_Shame-en-0-seed1701-scale0.0", "bucket": "emo_Shame", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "5c20b53d46e17fbe0b8a588e67db11e0e6c6eafb160a6b4a5d8dd68abdc48617", "task_id": "emo_Shame-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.221180438995361, "genuineness": 3.9299514293670654, "identity": 0.4064827263355255, "hypothesis": "The 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_Shame/en/0fea3200772a448a85ed180d.mp3" }, { "key": "original-emo_Shame-en-0-seed1701-scale0.5", "bucket": "emo_Shame", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "326fd817980871d4a49ff1a511bb12e47bc49b995afe7d53d251dd86941d0932", "task_id": "emo_Shame-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.157639026641846, "genuineness": 4.042920112609863, "identity": 0.2101900279521942, "hypothesis": "The 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_Shame/en/bae74355bbe6c00935bdcc07.mp3" }, { "key": "original-emo_Shame-en-0-seed1701-scale0.75", "bucket": "emo_Shame", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "9cc66b8dad5ca4c7d06d244c7bdd638f6ec822c55e45523a1d3966749c85b052", "task_id": "emo_Shame-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.005438074469566345, "target_z": -0.3925781150029102, "ce": 6.252951145172119, "genuineness": 4.099404335021973, "identity": 0.2971625328063965, "hypothesis": "The 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_Shame/en/87f44921cf3279bf9da3064a.mp3" }, { "key": "original-emo_Shame-en-0-seed1701-scale1.0", "bucket": "emo_Shame", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "ed068f75fadd74fd04cb8190a1dd244c53eb935f932b9c0ff18a52e44cb4e501", "task_id": "emo_Shame-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.284721851348877, "genuineness": 4.049196243286133, "identity": 0.424969345331192, "hypothesis": "The 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_Shame/en/79626fe47745ec1ad90ba771.mp3" }, { "key": "original-emo_Shame-en-0-seed1702-scale0.0", "bucket": "emo_Shame", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "f7082d26de1ca7ef2ba0012724a5b4cf0a5c18f598ea7ffd37e08163b4df35f1", "task_id": "emo_Shame-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.008508503437042236, "target_z": -0.3867187575533568, "ce": 6.117925643920898, "genuineness": 4.042920112609863, "identity": 0.29750919342041016, "hypothesis": "The 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_Shame/en/01dc4ed63e4cd23c1bf80112.mp3" }, { "key": "original-emo_Shame-en-0-seed1702-scale0.5", "bucket": "emo_Shame", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "1df8c5c4451f5a749b56327333d3d4b901ee9d574f3bd5dbdad813cccf32bffa", "task_id": "emo_Shame-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.011578947305679321, "target_z": -0.3808593716676367, "ce": 6.205295085906982, "genuineness": 3.735394239425659, "identity": 0.2550375461578369, "hypothesis": "The 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_Shame/en/0f82f29a333990de554ab556.mp3" }, { "key": "original-emo_Shame-en-0-seed1702-scale0.75", "bucket": "emo_Shame", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "8d919e0d9a24b419d44c115ea8d33ba466387bca6991e3cf6c0da6266d9d9c22", "task_id": "emo_Shame-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.109982967376709, "genuineness": 3.9299514293670654, "identity": 0.21732944250106812, "hypothesis": "The 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_Shame/en/16e7adb34c177a91cef46710.mp3" }, { "key": "original-emo_Shame-en-0-seed1702-scale1.0", "bucket": "emo_Shame", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "3ed80a4f3a6a4c8ea4f7e9e49d38a424ed772f24e3199bee4f7ec555a6ca3108", "task_id": "emo_Shame-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 6.348263263702393, "genuineness": 4.1998209953308105, "identity": 0.2892913222312927, "hypothesis": "The 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_Shame/en/0bc525b17211a733a2263922.mp3" }, { "key": "original-emo_Shame-en-1-seed1701-scale0.0", "bucket": "emo_Shame", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "ece04ac98123c6c26585b0e24ef72a0a81b24536432c0b32203f9a15be211a8b", "task_id": "emo_Shame-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.0058201998472213745, "target_z": -0.41406249200232814, "ce": 6.3641486167907715, "genuineness": 4.2374773025512695, "identity": 0.45691370964050293, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/en/ace2b71177a0dce3536a90b6.mp3" }, { "key": "original-emo_Shame-en-1-seed1701-scale0.5", "bucket": "emo_Shame", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "466f8cfcd79e77860ab856e65b0ac564ff249217cb2232a1d598ff4646a24a27", "task_id": "emo_Shame-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.02117238938808441, "target_z": -0.44335936455859504, "ce": 6.41180419921875, "genuineness": 4.482243061065674, "identity": 0.4506463408470154, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/en/13f5996c4c196a717db0b25d.mp3" }, { "key": "original-emo_Shame-en-1-seed1701-scale0.75", "bucket": "emo_Shame", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "4443471809ce55a28a1abcac991ff534fad00af48db6b1bc1db1cbe4e102ef8a", "task_id": "emo_Shame-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.004796728491783142, "target_z": -0.4121093823311992, "ce": 6.348263263702393, "genuineness": 4.720732688903809, "identity": 0.5731735229492188, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/en/b8be8d973c9df5bd888c7768.mp3" }, { "key": "original-emo_Shame-en-1-seed1701-scale1.0", "bucket": "emo_Shame", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "07edbab1d2f55a7b484454d805e69aa29865dea4136408f1e8688ba30e4f0ef8", "task_id": "emo_Shame-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.011961087584495544, "target_z": -0.42578126377376824, "ce": 6.41180419921875, "genuineness": 4.319066047668457, "identity": 0.35961490869522095, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/en/3c01f4396c5fc8e968f80837.mp3" }, { "key": "original-emo_Shame-en-1-seed1702-scale0.0", "bucket": "emo_Shame", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "6e409e5f3eec55d18cc616525139406b2942fa3ceb98adc32c9df7c4b250ac07", "task_id": "emo_Shame-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.014008045196533203, "target_z": -0.4296875115521927, "ce": 6.395919322967529, "genuineness": 4.6203155517578125, "identity": 0.3796389698982239, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/en/d65d918b793d89c109e02948.mp3" }, { "key": "original-emo_Shame-en-1-seed1702-scale0.5", "bucket": "emo_Shame", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "80a8ae8272dd469ff6a3ee297cdffd92d591f46327a2cbac77faadfafb0cde8e", "task_id": "emo_Shame-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.001344144344329834, "target_z": -0.4003906389959258, "ce": 6.3641486167907715, "genuineness": 4.337893962860107, "identity": 0.5423464775085449, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/en/179be603400527cb25318a7d.mp3" }, { "key": "original-emo_Shame-en-1-seed1702-scale0.75", "bucket": "emo_Shame", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "4192d391dc7bbb21ab8da9bf6b86f69935e91a22dbc395b8a38b1e115024d184", "task_id": "emo_Shame-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.009914115071296692, "target_z": -0.4218749875591771, "ce": 6.443574905395508, "genuineness": 4.494794845581055, "identity": 0.2996568977832794, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/en/92437091ae9162f6ce4e9589.mp3" }, { "key": "original-emo_Shame-en-1-seed1702-scale1.0", "bucket": "emo_Shame", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "3d44092b36ea82d3956ceeaaa3451ad6e92cc4cb99c0dbbf5157065ed4744033", "task_id": "emo_Shame-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.014008045196533203, "target_z": -0.4296875115521927, "ce": 6.23706579208374, "genuineness": 4.400654315948486, "identity": 0.40604883432388306, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/en/bf816b10dbe8ca6a486cdc8a.mp3" }, { "key": "original-emo_Shame-es-0-seed1701-scale0.0", "bucket": "emo_Shame", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "a85cfbb0de783d82d60eb5255a1000909bee31b358e7acb09f9085c404f02dfb", "task_id": "emo_Shame-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.141753673553467, "genuineness": 4.193545341491699, "identity": 0.5388215780258179, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/f811bf3d8d37befcd08fa909.mp3" }, { "key": "original-emo_Shame-es-0-seed1701-scale0.5", "bucket": "emo_Shame", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "469524b83a1cabce3a15e6e32be6a98d01cc23c2f2a3630189b6116f0e6e8b2b", "task_id": "emo_Shame-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.02693113684654236, "target_z": -0.3515624991113698, "ce": 5.927301406860352, "genuineness": 4.036643981933594, "identity": 0.5263514518737793, "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_Shame/es/4ff7d192c20279891fbe6236.mp3" }, { "key": "original-emo_Shame-es-0-seed1701-scale0.75", "bucket": "emo_Shame", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "e81262a7ace8dd1bccfcade30bbdb10330f219a61c5d4c32a5b12d316cef8ffe", "task_id": "emo_Shame-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.019766777753829956, "target_z": -0.3652343805539388, "ce": 6.221180438995361, "genuineness": 4.168440818786621, "identity": 0.5332621335983276, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/0571df0547860135832eb9a2.mp3" }, { "key": "original-emo_Shame-es-0-seed1701-scale1.0", "bucket": "emo_Shame", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "aa9006ad441064bfdcd9667ab18f3f934bd882192193d371dc77eb084bea7dbd", "task_id": "emo_Shame-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.982900142669678, "genuineness": 4.243753433227539, "identity": 0.45767298340797424, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/1a554bac2e2683a5947620b1.mp3" }, { "key": "original-emo_Shame-es-0-seed1702-scale0.0", "bucket": "emo_Shame", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "7222ddef600de64a97b2329edffa1e9035d696ac46fa13bfbf7435ed8f231496", "task_id": "emo_Shame-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.03614245355129242, "target_z": -0.3339843698903763, "ce": 5.871703147888184, "genuineness": 4.174716949462891, "identity": 0.6836448907852173, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/f94f81142260d466090b17fc.mp3" }, { "key": "original-emo_Shame-es-0-seed1702-scale0.5", "bucket": "emo_Shame", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "1695631086516e134f5218b8873b68c12f21b3eaa82c1ee0352ae9892f55ee34", "task_id": "emo_Shame-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 5.959072113037109, "genuineness": 4.174716949462891, "identity": 0.7319501638412476, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/aca1cdb49dcf4c444be58d8d.mp3" }, { "key": "original-emo_Shame-es-0-seed1702-scale0.75", "bucket": "emo_Shame", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "386ace803abb85c19bd7341649b8580d4c81f7fbbcca9c54d0a2b7aa23ca374f", "task_id": "emo_Shame-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.181467056274414, "genuineness": 4.086852550506592, "identity": 0.46467137336730957, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/9cc14271406a4705c5b190b4.mp3" }, { "key": "original-emo_Shame-es-0-seed1702-scale1.0", "bucket": "emo_Shame", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "01859772307e6a28c3821a31a510289c8eafacf992c320d16300970362f827d5", "task_id": "emo_Shame-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 5.998785495758057, "genuineness": 4.457139015197754, "identity": 0.5494064688682556, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/1ed1ce7784edfe994aea9cd9.mp3" }, { "key": "original-emo_Shame-es-1-seed1701-scale0.0", "bucket": "emo_Shame", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "9e84c1c676d77ba7eb0e12bc2f5d96ba20ada6d9f9bdc8906508ccb9af70c945", "task_id": "emo_Shame-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.009914115071296692, "target_z": -0.4218749875591771, "ce": 6.268836498260498, "genuineness": 4.758388519287109, "identity": 0.5854775905609131, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/df809ae2c4a2e451556a7640.mp3" }, { "key": "original-emo_Shame-es-1-seed1701-scale0.5", "bucket": "emo_Shame", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "695a2686e2e7054774ae0201a91efc9c6b1fcd20afcf3ccd0a56f3828d7cb0b6", "task_id": "emo_Shame-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.011961087584495544, "target_z": -0.42578126377376824, "ce": 6.252951145172119, "genuineness": 4.6705241203308105, "identity": 0.6539477109909058, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/f797633bdbfdbbae3ca4e9df.mp3" }, { "key": "original-emo_Shame-es-1-seed1701-scale0.75", "bucket": "emo_Shame", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "2656036eda08bc96e174296430b4fe686d1010439073a232a65adce316a5863c", "task_id": "emo_Shame-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.004796728491783142, "target_z": -0.4121093823311992, "ce": 6.157639026641846, "genuineness": 4.607763767242432, "identity": 0.574459433555603, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/26a7e03a225db31cb564b8da.mp3" }, { "key": "original-emo_Shame-es-1-seed1701-scale1.0", "bucket": "emo_Shame", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "c46734699e5739cca8ad3bbe86ea70eecb7cfc0dfb3241acdd6946ca3076c97d", "task_id": "emo_Shame-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 6.054384231567383, "genuineness": 4.7332844734191895, "identity": 0.652528703212738, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/7389d1e17af1a546e78355eb.mp3" }, { "key": "original-emo_Shame-es-1-seed1702-scale0.0", "bucket": "emo_Shame", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "7163430b2ba2e443d212aaae8cfc7eb76dfafb9dc7595c39f2d19e3a0e02f001", "task_id": "emo_Shame-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.1020402908325195, "genuineness": 4.7081804275512695, "identity": 0.720954418182373, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/55ae66a7168f5257fab6a519.mp3" }, { "key": "original-emo_Shame-es-1-seed1702-scale0.5", "bucket": "emo_Shame", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "33d3bcf2dbeec8642c41f30cd5398c34d1ae01a57ae37b825f0a87d8493da64b", "task_id": "emo_Shame-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.0027497708797454834, "target_z": -0.40820313455277474, "ce": 6.221180438995361, "genuineness": 4.482243061065674, "identity": 0.5924111604690552, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/c2efad04d5523aafc6affebd.mp3" }, { "key": "original-emo_Shame-es-1-seed1702-scale0.75", "bucket": "emo_Shame", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "1f3c6977ab3d07b1cd0bc9421c0b723a6668d9ce2fe1dc34a176bc2cbbef8c0e", "task_id": "emo_Shame-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.0007028132677078247, "target_z": -0.4042968867743503, "ce": 5.935244083404541, "genuineness": 4.582659721374512, "identity": 0.6525847911834717, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/31485a7a18a92bd5266057ab.mp3" }, { "key": "original-emo_Shame-es-1-seed1702-scale1.0", "bucket": "emo_Shame", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "4d4f8db8148c0a11356dce6c1cc0ec0cc36829a4b5f4c7e829c87ca711b1682e", "task_id": "emo_Shame-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.0027497708797454834, "target_z": -0.40820313455277474, "ce": 6.1894097328186035, "genuineness": 4.871357440948486, "identity": 0.5653926134109497, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/es/b69c327ef2c030a4fb94ed00.mp3" }, { "key": "original-emo_Shame-fr-0-seed1701-scale0.0", "bucket": "emo_Shame", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "5f8f7cfe7620957c320cf0edc78f91176eef7b6689985ba95b4a44ca9a9b84c2", "task_id": "emo_Shame-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.024242833256721497, "target_z": -0.4492187504443151, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.8266106843948364, "hypothesis": "La porte 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_Shame/fr/9701bfaf486a3c55ed731eb4.mp3" }, { "key": "original-emo_Shame-fr-0-seed1701-scale0.5", "bucket": "emo_Shame", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "3e5424b3bb149e548a6534992b0a8c8bd12b2dc7b51cc526830501e979201b54", "task_id": "emo_Shame-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.023860692977905273, "target_z": -0.3574218849970898, "ce": 6.09409761428833, "genuineness": 4.381826400756836, "identity": 0.7508149743080139, "hypothesis": "La porte 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_Shame/fr/2b612def4c27afe2a74ac6ff.mp3" }, { "key": "original-emo_Shame-fr-0-seed1701-scale0.75", "bucket": "emo_Shame", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "0084f803baf64af6ec40d785a01308c120ff069d277c8c0b689c19b51dc9642c", "task_id": "emo_Shame-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.078212261199951, "genuineness": 4.482243061065674, "identity": 0.808281660079956, "hypothesis": "La porte 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_Shame/fr/d1185c1651528bf281344373.mp3" }, { "key": "original-emo_Shame-fr-0-seed1701-scale1.0", "bucket": "emo_Shame", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "2ad67de31df05ae4431bc9fb5205e43ec4d7d8381575e517de12e32863202f5f", "task_id": "emo_Shame-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.007867157459259033, "target_z": -0.4179687397807526, "ce": 6.046441555023193, "genuineness": 4.532451152801514, "identity": 0.7921362519264221, "hypothesis": "La porte est alors encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/fr/3c114ff5ab267d7de6bbd795.mp3" }, { "key": "original-emo_Shame-fr-0-seed1702-scale0.0", "bucket": "emo_Shame", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "1fd2a78c0313745ff86fe901bf4a311733004402b67adc9661109bdc7825e2aa", "task_id": "emo_Shame-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.078212261199951, "genuineness": 4.457139015197754, "identity": 0.7944614887237549, "hypothesis": "La porte 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_Shame/fr/466de59128ad9fbbc9634093.mp3" }, { "key": "original-emo_Shame-fr-0-seed1702-scale0.5", "bucket": "emo_Shame", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "e630fac01a446fad7151ab1c0b5fe59722350c641bde481eab2fc2f273d37dc9", "task_id": "emo_Shame-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.0248841792345047, "target_z": -0.3554687468897943, "ce": 6.221180438995361, "genuineness": 4.356721878051758, "identity": 0.7290444374084473, "hypothesis": "La porte 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_Shame/fr/8a2fcc1aec51a973b89e3956.mp3" }, { "key": "original-emo_Shame-fr-0-seed1702-scale0.75", "bucket": "emo_Shame", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "e67929fc21ab8cae6adbd244a8d62d153c751dd6b274c0f1fada4f45c277f2a1", "task_id": "emo_Shame-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.016696348786354065, "target_z": -0.3710937380034922, "ce": 6.062326908111572, "genuineness": 4.306513786315918, "identity": 0.8970199227333069, "hypothesis": "La porte 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_Shame/fr/36512bb5496bb0f7bf554f2f.mp3" }, { "key": "original-emo_Shame-fr-0-seed1702-scale1.0", "bucket": "emo_Shame", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "0ee1ac2d5ba656474770e6d85d44a54f7ba54f9d165fac420cd349b208ba111b", "task_id": "emo_Shame-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.117925643920898, "genuineness": 4.2374773025512695, "identity": 0.6853101253509521, "hypothesis": "La porte 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_Shame/fr/8299bbb2900a29d234f2a6a9.mp3" }, { "key": "original-emo_Shame-fr-1-seed1701-scale0.0", "bucket": "emo_Shame", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "9eca86ddfbf0c7014c25814a916f91fd16267d581cd6da853af627687eed4b85", "task_id": "emo_Shame-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.004414588212966919, "target_z": -0.3945312531102057, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.6880730986595154, "hypothesis": "J'ai trouvé la 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_Shame/fr/b810bb6126cfcd937f2c4daf.mp3" }, { "key": "original-emo_Shame-fr-1-seed1701-scale0.5", "bucket": "emo_Shame", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "b6458f5c73bc2afe33d3fa3686e0db3dc38b08fc652254e79660bd74c7a855ec", "task_id": "emo_Shame-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 5.935244083404541, "genuineness": 4.6203155517578125, "identity": 0.6810678243637085, "hypothesis": "J'ai trouvé la 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_Shame/fr/1a81a3fb72a708321d3d1d9a.mp3" }, { "key": "original-emo_Shame-fr-1-seed1701-scale0.75", "bucket": "emo_Shame", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "984253687f3ea7b9c16b62fc1b2ebb6d2001108b58685e55f496247d65f24ce5", "task_id": "emo_Shame-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.6301993727684021, "hypothesis": "J'ai trouvé la 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_Shame/fr/e1f4f7428daf544dc0044869.mp3" }, { "key": "original-emo_Shame-fr-1-seed1701-scale1.0", "bucket": "emo_Shame", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "1750ce3417a824527a778d2055dfba25534745d2c78fba23551caf0632cd6567", "task_id": "emo_Shame-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.018743306398391724, "target_z": -0.3671874902250677, "ce": 6.078212261199951, "genuineness": 4.457139015197754, "identity": 0.7313389778137207, "hypothesis": "J'ai trouvé la 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_Shame/fr/d2a83e0f42eec46b587df85b.mp3" }, { "key": "original-emo_Shame-fr-1-seed1702-scale0.0", "bucket": "emo_Shame", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "bbe3bdf7572252b6202468a984b27d64336575ec3d62987fea09dbf718d9be12", "task_id": "emo_Shame-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.009531989693641663, "target_z": -0.3847656194460612, "ce": 6.133810997009277, "genuineness": 4.293961524963379, "identity": 0.6651834845542908, "hypothesis": "J'ai trouvé la 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_Shame/fr/b6af56672f40da36bf8eedda.mp3" }, { "key": "original-emo_Shame-fr-1-seed1702-scale0.5", "bucket": "emo_Shame", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "64439bb0764cb7376295399adf66d166fd3df6967a8e8cdbabd2e03c9ee69367", "task_id": "emo_Shame-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.014649376273155212, "target_z": -0.3750000142180833, "ce": 6.0305562019348145, "genuineness": 4.406930446624756, "identity": 0.7664754390716553, "hypothesis": "J'ai trouvé la 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_Shame/fr/076234106544d1bfa8dd31b1.mp3" }, { "key": "original-emo_Shame-fr-1-seed1702-scale0.75", "bucket": "emo_Shame", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "ff76d3727f9925c634ab3fed7f852659f077915a05e2f0076786f1f88b74b1b2", "task_id": "emo_Shame-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.012602418661117554, "target_z": -0.3789062619965078, "ce": 6.23706579208374, "genuineness": 4.400654315948486, "identity": 0.7736820578575134, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/fr/f5dc9e8ecdcf8849cfd47eef.mp3" }, { "key": "original-emo_Shame-fr-1-seed1702-scale1.0", "bucket": "emo_Shame", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "ddd7d04a3a8eb122f63282dc8f4636a8ca5166f0f92b7f8ce1ad646c3c3bee5f", "task_id": "emo_Shame-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.020790264010429382, "target_z": -0.3632812424466432, "ce": 6.141753673553467, "genuineness": 4.381826400756836, "identity": 0.6233819723129272, "hypothesis": "J'ai trouvé la 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_Shame/fr/1fbc79f138305d872d19d7fc.mp3" }, { "key": "original-emo_Shame-nl-0-seed1701-scale0.0", "bucket": "emo_Shame", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "16c88df9c4b847a37c6005310c2f5e802e6e5264f6f21f09de446ab5b104c86a", "task_id": "emo_Shame-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.133810997009277, "genuineness": 4.344170093536377, "identity": 0.6864643096923828, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/2863bacec6b2201b4dc1aa88.mp3" }, { "key": "original-emo_Shame-nl-0-seed1701-scale0.5", "bucket": "emo_Shame", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "63f20b9be94b3f080933e71cceee69b12dc7402e38e03dd0ad112b899cd4f756", "task_id": "emo_Shame-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.05047115683555603, "target_z": -0.30664063544140496, "ce": 6.205295085906982, "genuineness": 4.362998008728027, "identity": 0.6250619888305664, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/5a17f7c91879ce7af131515e.mp3" }, { "key": "original-emo_Shame-nl-0-seed1701-scale0.75", "bucket": "emo_Shame", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "fa6d484996a25bdc7dc2851e0727ad2e699d62e60af086fbf189debf63777e21", "task_id": "emo_Shame-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.03614245355129242, "target_z": -0.3339843698903763, "ce": 6.205295085906982, "genuineness": 4.331617832183838, "identity": 0.6203048825263977, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/359e42feabd41a7d4a5bbbdf.mp3" }, { "key": "original-emo_Shame-nl-0-seed1701-scale1.0", "bucket": "emo_Shame", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "969597c1ed53c20f933c9e778017828d63f950e403d9aa288da62be0b723602e", "task_id": "emo_Shame-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.04125985503196716, "target_z": -0.32421873622623176, "ce": 6.109982967376709, "genuineness": 4.369274139404297, "identity": 0.5852824449539185, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/49968659f40f25024ddd9b22.mp3" }, { "key": "original-emo_Shame-nl-0-seed1702-scale0.0", "bucket": "emo_Shame", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "a9a63d13b57a78969c29567216e615be27592dedf7e8145e9e28d2f3b5f3cc73", "task_id": "emo_Shame-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 6.1894097328186035, "genuineness": 4.325342178344727, "identity": 0.7208220958709717, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/c94bf60b3a5c0170ff0215a6.mp3" }, { "key": "original-emo_Shame-nl-0-seed1702-scale0.5", "bucket": "emo_Shame", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "120f5d065a0426278b9138d2173837f8cf78a2fc04af6a5a74bf048efe834deb", "task_id": "emo_Shame-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.028978094458580017, "target_z": -0.3476562513329453, "ce": 6.181467056274414, "genuineness": 4.231201171875, "identity": 0.6222925782203674, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/2f27b6bb8faf9cb047336485.mp3" }, { "key": "original-emo_Shame-nl-0-seed1702-scale0.75", "bucket": "emo_Shame", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "f13921621ab548675590b1498ceb6d9301f51c7741c467d7d11d196579cb3750", "task_id": "emo_Shame-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.042283326387405396, "target_z": -0.3222656265551029, "ce": 6.165581703186035, "genuineness": 4.2374773025512695, "identity": 0.8023386001586914, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/e1ecc46a5845d800a9c52004.mp3" }, { "key": "original-emo_Shame-nl-0-seed1702-scale1.0", "bucket": "emo_Shame", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "847946a343c6f20682f81d8df44427d0ec21664ebdd486dba207b51b80a23de5", "task_id": "emo_Shame-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.7897303104400635, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/93500742bd5eee47f305da36.mp3" }, { "key": "original-emo_Shame-nl-1-seed1701-scale0.0", "bucket": "emo_Shame", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "47a521bef031ffe30703d91fe25c0f1d128bb376f2f2c7916fc3b859f7129626", "task_id": "emo_Shame-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.06889379024505615, "target_z": -0.27148437699941796, "ce": 6.086154937744141, "genuineness": 4.137060642242432, "identity": 0.5030832290649414, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/ca232516d7a5cde28404ca52.mp3" }, { "key": "original-emo_Shame-nl-1-seed1701-scale0.5", "bucket": "emo_Shame", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "ebdb12c36149921caf95d1c244995eb8ea3f60d3da70050134db6e1cb74c7e1c", "task_id": "emo_Shame-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.03409549593925476, "target_z": -0.3378906176688008, "ce": 5.95112943649292, "genuineness": 4.287685871124268, "identity": 0.43696117401123047, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/3b027b70f8f0b412f2c772bc.mp3" }, { "key": "original-emo_Shame-nl-1-seed1701-scale0.75", "bucket": "emo_Shame", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "0701801613ef1d7b9ee4f008de222ade7d82eb627abb503c51f089c23d4230be", "task_id": "emo_Shame-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.04330681264400482, "target_z": -0.3203124884478073, "ce": 6.197352409362793, "genuineness": 4.293961524963379, "identity": 0.672728419303894, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/203e67203a418b90b69965be.mp3" }, { "key": "original-emo_Shame-nl-1-seed1701-scale1.0", "bucket": "emo_Shame", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "3d6819c9e8871a7ce383a570388111e60f5dc5fdc9b8e1d156fdcf36aaa0ab16", "task_id": "emo_Shame-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.033072009682655334, "target_z": -0.3398437557760964, "ce": 6.221180438995361, "genuineness": 4.256305694580078, "identity": 0.6976988315582275, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/2b074bd8973dd63a38dcaa03.mp3" }, { "key": "original-emo_Shame-nl-1-seed1702-scale0.0", "bucket": "emo_Shame", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "e340929ad4b2d69e1d7073c6e78b137055c3b7e5a4ee388e46b7f495f5a057a6", "task_id": "emo_Shame-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.025907650589942932, "target_z": -0.35351563721866536, "ce": 6.1020402908325195, "genuineness": 4.482243061065674, "identity": 0.6812957525253296, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/bb1a11749da29407d2243371.mp3" }, { "key": "original-emo_Shame-nl-1-seed1702-scale0.5", "bucket": "emo_Shame", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "92886302bb178925dfa0ce9a1146fa6733321ecca9d88ac4bdccd15fb5735ceb", "task_id": "emo_Shame-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.02283722162246704, "target_z": -0.35937499466821876, "ce": 6.157639026641846, "genuineness": 4.337893962860107, "identity": 0.7620230913162231, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/e6668995d431f51828515452.mp3" }, { "key": "original-emo_Shame-nl-1-seed1702-scale0.75", "bucket": "emo_Shame", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "6efb20f2d076518cd0084412feb053499d7b60984a01e14a8516981084aa9218", "task_id": "emo_Shame-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": 0.021813735365867615, "target_z": -0.36132813277551434, "ce": 6.086154937744141, "genuineness": 4.432034492492676, "identity": 0.3930395841598511, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/fd935bfd5ed250fd760f966a.mp3" }, { "key": "original-emo_Shame-nl-1-seed1702-scale1.0", "bucket": "emo_Shame", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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 Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e3cfe121d0ea430b4bf8eb611d2fc7407b0ab635c94ef035e69237df6297fb79", "mp3_sha256": "0b75e91670539a10096525e3152cea9e17681b56e04ec93a437d92f4f733d228", "task_id": "emo_Shame-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Shame. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Shame. 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 Shame. 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 Shame. 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": -0.003773242235183716, "target_z": -0.4101562442239036, "ce": 5.871703147888184, "genuineness": 4.381826400756836, "identity": 0.6195642948150635, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Shame/nl/6369b6e55f2f8ad029fc7de9.mp3" } ], "source_standard_audio_unchanged": true }