{ "complete": true, "report": { "bucket": "emo_Jealousy_and_Envy", "label": "Intense Jealousy and Envy", "definition": { "id": "emo_Jealousy_and_Envy", "category": "emotion", "head": "emo_Jealousy_and_Envy", "pole": "high", "label": "Intense Jealousy and Envy", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_jealousy_and_envy/full-v2-sealed/sealed-selected", "mission": "emotion_jealousy_and_envy", "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": 6.321734676361084, "genuineness": 4.4833098936080935, "wer": 0.0049000097845342564, "identity": 0.601659426689148, "voiceclap": -0.20070551186800004, "fitness": 0.5082160390534568, "steering_v2": 0.3317885387501862, "raw_target": 0.020643950402736665, "target_cdf": 0.3317885387501862, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.35191686630249, "genuineness": 4.486761722564697, "wer": 0.003206989247311828, "identity": 0.601659426689148, "fitness": 0.5099728517925696, "steering_v2": 0.33175521760509974 }, "none": { "n": 50, "ce": 6.291552486419678, "genuineness": 4.47985806465149, "wer": 0.006593030321756684, "identity": null, "fitness": 0.506459226314344, "steering_v2": 0.33182185989527274 } } } } ], "selected_wording": { "id": "manual-c1306bd27b08", "general": "Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.", "inline": [ "Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.", "Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.", "Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment." ], "cfg": 3, "recipe": "P02", "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": -0.4402343703774424, "target_raw": 0.018406446278095245, "ce": 5.851002311706543, "genuineness": 4.4787911653518675, "identity": 0.6251532971858978, "wer": 0.01625, "valid_fraction": 1, "identity_delta": 0.11914364844560624, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": -0.4424804674637799, "target_raw": 0.017405226081609725, "ce": 5.780957889556885, "genuineness": 4.483184385299682, "identity": 0.5726504646241665, "wer": 0.015674019607843138, "valid_fraction": 1, "identity_delta": 0.0666408158838749, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": -0.4402343703774424, "target_raw": 0.018406446278095245, "ce": 5.851002311706543, "genuineness": 4.4787911653518675, "identity": 0.6251532971858978, "wer": 0.01625, "valid_fraction": 1, "identity_delta": 0.11914364844560624, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": -0.4441406252350453, "target_raw": 0.016665194183588028, "ce": 5.691900706291198, "genuineness": 4.439565896987915, "identity": 0.5648918226361275, "wer": 0.009089912280701754, "valid_fraction": 1, "identity_delta": 0.058882173895835874, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.45673828290184615, "target_raw": 0.011049662530422211, "ce": 5.935442733764648, "genuineness": 4.46027684211731, "identity": 0.6183047287166119, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.11229507997632027, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.46171875120134265, "target_raw": 0.008829569071531295, "ce": 6.044853091239929, "genuineness": 4.479732537269593, "identity": 0.5909344963729382, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.08492484763264656, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.46289062314575374, "target_raw": 0.008307195454835891, "ce": 6.109982991218567, "genuineness": 4.4844396114349365, "identity": 0.581739516556263, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": 0.07572986781597138, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.4653320322228264, "target_raw": 0.007218912988901138, "ce": 6.1266625881195065, "genuineness": 4.441448712348938, "identity": 0.5482073746621609, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.04219772592186928, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.47871093785256796, "target_raw": 0.001255132257938385, "ce": 6.147909235954285, "genuineness": 4.358918726444244, "identity": 0.5626051835715771, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.056595534831285474, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.47919921866512255, "target_raw": 0.0010374762117862702, "ce": 6.192189693450928, "genuineness": 4.436427843570709, "identity": 0.567296926677227, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.061287277936935426, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": -0.4424804674637799, "target_raw": 0.017405226081609725, "ce": 5.780957889556885, "genuineness": 4.483184385299682, "identity": 0.5726504646241665, "wer": 0.015674019607843138, "valid_fraction": 1, "identity_delta": 0.0666408158838749, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": -0.44277343795703256, "target_raw": 0.017274631559848784, "ce": 5.69974410533905, "genuineness": 4.434544956684112, "identity": 0.5541508927941322, "wer": 0.018223039215686274, "valid_fraction": 0.95, "identity_delta": 0.04814124405384064, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": -0.44423828039469626, "target_raw": 0.01662166342139244, "ce": 5.773114514350891, "genuineness": 4.430151867866516, "identity": 0.5639521718025208, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": 0.057942523062229155, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": -0.4466796861289024, "target_raw": 0.015533382445573807, "ce": 5.688872456550598, "genuineness": 4.41320652961731, "identity": 0.5556105107069016, "wer": 0.015054824561403508, "valid_fraction": 1, "identity_delta": 0.049600861966609955, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": -0.4498046880092648, "target_raw": 0.014140381664037704, "ce": 5.6175621509552, "genuineness": 4.377119302749634, "identity": 0.5815128162503242, "wer": 0.025909442724458203, "valid_fraction": 0.95, "identity_delta": 0.07550316751003265, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": -0.45097656496797567, "target_raw": 0.013618005812168122, "ce": 5.919358897209167, "genuineness": 4.502012467384338, "identity": 0.5829664409160614, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": 0.07695679217576981, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": -0.4521484352409535, "target_raw": 0.013095632940530778, "ce": 5.829507446289062, "genuineness": 4.469063258171081, "identity": 0.6147201716899872, "wer": 0.012239422084623322, "valid_fraction": 1, "identity_delta": 0.10871052294969559, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": -0.45322265369714687, "target_raw": 0.0126167893409729, "ce": 5.938024115562439, "genuineness": 4.51330931186676, "identity": 0.6237917952239513, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.11778214648365974, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": -0.4550781251305807, "target_raw": 0.011789694428443909, "ce": 5.990048670768738, "genuineness": 4.459963059425354, "identity": 0.6014304175972939, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.09542076885700226, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.4559570366103387, "target_raw": 0.011397910863161087, "ce": 5.982701659202576, "genuineness": 4.4929121971130375, "identity": 0.58314273878932, "wer": 0.012214912280701755, "valid_fraction": 1, "identity_delta": 0.0771330900490284, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": -0.4564453124085935, "target_raw": 0.011180257052183151, "ce": 5.916181850433349, "genuineness": 4.443645358085632, "identity": 0.5898286700248718, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.08381902128458023, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.45693359489258134, "target_raw": 0.010962600260972977, "ce": 5.989949345588684, "genuineness": 4.512681770324707, "identity": 0.6107218392193318, "wer": 0.014379084967320262, "valid_fraction": 0.95, "identity_delta": 0.10471219047904015, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.4580078133487747, "target_raw": 0.0104837566614151, "ce": 6.142945051193237, "genuineness": 4.453373157978058, "identity": 0.5885143026709556, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.08250465393066406, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.45830078049916084, "target_raw": 0.01035316362977028, "ce": 6.053192901611328, "genuineness": 4.441448676586151, "identity": 0.5613562136888504, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.05534656494855881, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": -0.4601562552754612, "target_raw": 0.009526067227125169, "ce": 6.061532735824585, "genuineness": 4.528999495506286, "identity": 0.6004076682031154, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.09439801946282386, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.4628906264886202, "target_raw": 0.008307193964719772, "ce": 6.112762904167175, "genuineness": 4.416658353805542, "identity": 0.5791321262717247, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": 0.07312247753143311, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.46367187110869446, "target_raw": 0.007958946377038955, "ce": 6.061532688140869, "genuineness": 4.441448676586151, "identity": 0.6349435240030289, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": 0.12893387526273728, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.4673828123041289, "target_raw": 0.006304757297039032, "ce": 6.152476286888122, "genuineness": 4.392495584487915, "identity": 0.5469940442591905, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.040984395518898965, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.46855468424853997, "target_raw": 0.005782383680343628, "ce": 6.109982991218567, "genuineness": 4.447410964965821, "identity": 0.6130470030009747, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.10703735426068306, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.4689453115728769, "target_raw": 0.00560825765132904, "ce": 6.113755750656128, "genuineness": 4.385278105735779, "identity": 0.5824510708451272, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": 0.07644142210483551, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.469335940568647, "target_raw": 0.005434130877256393, "ce": 6.132222461700439, "genuineness": 4.474084138870239, "identity": 0.6267715461552144, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.12076189741492271, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.4708007779920109, "target_raw": 0.004781164973974228, "ce": 6.144930720329285, "genuineness": 4.371470856666565, "identity": 0.5772015579044819, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0711919091641903, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.4736328143934205, "target_raw": 0.003518756479024887, "ce": 6.137583756446839, "genuineness": 4.369588041305542, "identity": 0.575085348635912, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.06907569989562035, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.4747070311781806, "target_raw": 0.00303991362452507, "ce": 6.183849859237671, "genuineness": 4.4568249702453615, "identity": 0.5761031717061996, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.07009352296590805, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.4747070295067473, "target_raw": 0.00303991436958313, "ce": 6.182658433914185, "genuineness": 4.338835453987121, "identity": 0.5060096487402916, "wer": 0.003125, "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": -0.4833007821705941, "target_raw": -0.0007908366620540619, "ce": 6.215223431587219, "genuineness": 4.279213094711304, "identity": 0.5827933371067047, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.07678368836641311, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.4783203121996643, "target_raw": 0.0014292575418949128, "ce": 6.210854959487915, "genuineness": 4.38527809381485, "identity": 0.5863860830664634, "wer": 0.016666666666666666, "valid_fraction": 0.95, "identity_delta": 0.08037643432617188, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.48388672148566614, "target_raw": -0.0010520249605178833, "ce": 6.223563218116761, "genuineness": 4.3739812731742855, "identity": 0.5693821609020233, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.06337251216173172, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.48046875212063095, "target_raw": 0.0004715690016746521, "ce": 6.263117752075195, "genuineness": 4.361742987632751, "identity": 0.5780346509814263, "wer": 0.005631469979296066, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": -0.45957031462324255, "target_raw": 0.009787256121635437, "ce": 5.977022657394409, "genuineness": 4.542367429733276, "identity": 0.588259008526802, "wer": 0.02363081121776774, "valid_fraction": 0.98, "identity_delta": 0.010224357545375824, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": -0.4619531232502183, "target_raw": 0.008725095391273498, "ce": 5.955736312866211, "genuineness": 4.519522638320923, "identity": 0.5942593382298946, "wer": 0.04115859807621821, "valid_fraction": 0.92, "identity_delta": 0.0162246872484684, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": -0.45957031462324255, "target_raw": 0.009787256121635437, "ce": 5.977022657394409, "genuineness": 4.542367429733276, "identity": 0.588259008526802, "wer": 0.02363081121776774, "valid_fraction": 0.98, "identity_delta": 0.010224357545375824, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.0023828086269757406, "ci95_z": [ -0.008828122707002494, 0.005742194256246636 ], "language_deltas": { "en": -0.011523429182007916, "de": 0.012695324526484631, "fr": -0.00019531031930192233, "nl": -0.004687501149110357, "es": -0.00820312701094314 }, "languages_improved": 1, "clear_gain": false, "delta_ce": -0.02128634452819824, "delta_genuineness": -0.022844791412353516, "delta_wer": 0.017527786858450474, "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": -0.0023828086269757406, "ci95_z": [ -0.008828122707002494, 0.005742194256246636 ], "language_deltas": { "en": -0.011523429182007916, "de": 0.012695324526484631, "fr": -0.00019531031930192233, "nl": -0.004687501149110357, "es": -0.00820312701094314 }, "languages_improved": 1, "clear_gain": false, "delta_ce": -0.02128634452819824, "delta_genuineness": -0.022844791412353516, "delta_wer": 0.017527786858450474, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.020898437497388383, "ci95_z": [ 0.01277343661988592, 0.029023438374890846 ], "language_deltas": { "en": 0.015429682368177577, "de": 0.011914056506344783, "fr": 0.01230469385928123, "nl": 0.03378905964028216, "es": 0.031054695112856173 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.28609509468078614, "delta_genuineness": 0.1806244421005249, "delta_wer": 0.01799934123847167, "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": 1793035456.265707, "example": { "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "sentences": [ "J’ai écrit le numéro sur l’enveloppe.", "Lis-le bien... et vérifie les deux derniers chiffres.", "Appelle-moi quand tu auras un moment." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "language": "fr", "seed": 1701, "scale": 0.0, "cfg": 4.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "00756430c0c9ec325b379a2ef52f75a9d8f115e732babc7204e762a039f0ea82", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "df6ba39baf7b4595d13c467f1bcc5b37f5951ede5052361c19808fc7f50fc24a", "generation_seconds_batch": 33.43075503304135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029202193021774292, "target_z": -0.4160156266975494, "ce": 5.2045183181762695, "genuineness": 4.319066047668457, "identity": 0.7248795032501221, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/00756430c0c9ec325b379a2ef52f75a9d8f115e732babc7204e762a039f0ea82.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "0093af9055707cfdc46adf008db24ef5687d9b2f16669529d4f179321cbb0990", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cfd28ac3a2a60db49024d12e12a0fe3c014874b947995a8cc7563fafa47566a7", "generation_seconds_batch": 25.15482202998828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.903473377227783, "genuineness": 4.444586753845215, "identity": 0.6085218787193298, "hypothesis": "De deur 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_Jealousy_and_Envy/0093af9055707cfdc46adf008db24ef5687d9b2f16669529d4f179321cbb0990.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "00b0c277bca312f91126aad5884133f6e7906cf2e25500306efb6dd6173f1ce2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8eaf5e6d830be8ecb3fc93414ee26bb9cd977c7a595ffed35fefaa4e17d7e5db", "generation_seconds_batch": 24.709344442933798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 5.927301406860352, "genuineness": 4.557555198669434, "identity": 0.6868598461151123, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/00b0c277bca312f91126aad5884133f6e7906cf2e25500306efb6dd6173f1ce2.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "0163f6a9e4f8b59f14987baf0dcfd67f814d0fea972f9e0406351b9b86d1e681", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2d50feeb9ad3262233906427f4b6a6cdba8006db551a005f0a6c65a4fc67b70a", "generation_seconds_batch": 19.2082784390077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.790388286113739, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0163f6a9e4f8b59f14987baf0dcfd67f814d0fea972f9e0406351b9b86d1e681.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "0184a9db2688e1d3d1a10a11ac7b95925b446a6f0cdcd929d787e3d8f2eb1d30", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9374f9bfac4737a5429ee7693353fd1beea60d10a8b633c278208737ad44d6d0", "generation_seconds_batch": 18.218161099008285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 6.0146708488464355, "genuineness": 4.6203155517578125, "identity": 0.8434644937515259, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0184a9db2688e1d3d1a10a11ac7b95925b446a6f0cdcd929d787e3d8f2eb1d30.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "01ca60de533533b23951dc538a825d058d85534e93e7caf005a85969861855b3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f7dda52b8ee0f1c034a8e2fb3c4f52c099ebdaead0bcf334e60b9b6dd98a931b", "generation_seconds_batch": 18.76628469710704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 6.173524379730225, "genuineness": 4.532451152801514, "identity": 0.7417901754379272, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/01ca60de533533b23951dc538a825d058d85534e93e7caf005a85969861855b3.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "25c3544628e3e271481071a86cedc88b2fe400b81e82adf30fdcf20d10eff0e4", "generation_seconds_batch": 18.765271497890353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01694093644618988, "target_z": -0.5195312659308483, "ce": 6.062326908111572, "genuineness": 4.331617832183838, "identity": 0.6828200817108154, "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_Jealousy_and_Envy/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "0233f3a68cefccc85514b1d32641ccc64f73f31bf73865d26b536635b9d88a75", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a45783d1bc2ee947d20c2b833eb0f3a0f24094900cad8515f5999fe66b70e0fc", "generation_seconds_batch": 18.94928582198918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.173524379730225, "genuineness": 4.256305694580078, "identity": 0.6841616630554199, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0233f3a68cefccc85514b1d32641ccc64f73f31bf73865d26b536635b9d88a75.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "023f9bc5c8ea5351ce431bc0cc34f6bc377cb615d0adac276a8d744163483d6a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0b0ec506c03f45102e348c7670de91d01f6a13f9d7bd65f0d5bb9278d7934754", "generation_seconds_batch": 24.77463306696154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03007282316684723, "target_z": -0.41406249007586504, "ce": 5.637393951416016, "genuineness": 4.3881025314331055, "identity": 0.18741953372955322, "hypothesis": "De deur 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_Jealousy_and_Envy/023f9bc5c8ea5351ce431bc0cc34f6bc377cb615d0adac276a8d744163483d6a.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": "02472bc903f6acf01a75f2848f82f98fbdc1382b1fd6d4961f30fad42d3de42d", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "629e0c596a2cccda7d5b8844317356fce3775b1efb5ca879707ed82c603b9e44", "generation_seconds_batch": 19.6787010099506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 5.49045467376709, "genuineness": 4.7081804275512695, "identity": 0.8043915033340454, "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_Jealousy_and_Envy/02472bc903f6acf01a75f2848f82f98fbdc1382b1fd6d4961f30fad42d3de42d.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "0261c07b2db8d6574a9a71fe209741e76383c90585e1c83be1a3fb4e9392ce18", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cd29101acf41f4cf7f29bfe218e8c2a1ddb9fe5a6e7ee79c0287234d7db4070e", "generation_seconds_batch": 25.022231738897972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 5.649308204650879, "genuineness": 4.394378662109375, "identity": 0.6632355451583862, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0261c07b2db8d6574a9a71fe209741e76383c90585e1c83be1a3fb4e9392ce18.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "0327ad07fd5d2a73c416614b0d1d05ded3bccfc6bf5060873735506ce8329662", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "95cb6a8f1875b711413af5e8d507c6def5fb04e1fb0f183e09094480c782cadc", "generation_seconds_batch": 26.196036829031073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.23706579208374, "genuineness": 4.118232727050781, "identity": 0.12012112885713577, "hypothesis": "The 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_Jealousy_and_Envy/0327ad07fd5d2a73c416614b0d1d05ded3bccfc6bf5060873735506ce8329662.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "04a5791777bb27d44e78e7e772775369a0eaadbe94dded5e5efe0c14983666aa", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ea005db80f24c4549c5c1bee7156b240b223acc2fda7d5432ef603820bd10811", "generation_seconds_batch": 25.390402112039737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.998785495758057, "genuineness": 4.8588056564331055, "identity": 0.7089309096336365, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/04a5791777bb27d44e78e7e772775369a0eaadbe94dded5e5efe0c14983666aa.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "04c370aebdb1c4aceb52c1d274c91a8b48ee9152557a4a39f89f3c0bc4ef3419", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "895163215cb13dc795293babbff89a458085866921b74ed39f2fc0632daa4542", "generation_seconds_batch": 19.91898058494553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.6008592844009399, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/04c370aebdb1c4aceb52c1d274c91a8b48ee9152557a4a39f89f3c0bc4ef3419.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "04e0843713eb70c14df0d4520a9789fd9e732e73cbf27ca890e4ab691f08e89c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fa4062f3b33c5018c24d104f55a0f04886ce77f018bdda4a47fc644ed532a0f3", "generation_seconds_batch": 24.22881351201795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.046441555023193, "genuineness": 4.570107460021973, "identity": 0.7585970163345337, "hypothesis": "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_Jealousy_and_Envy/04e0843713eb70c14df0d4520a9789fd9e732e73cbf27ca890e4ab691f08e89c.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "491fbc749a9e06db6d638507de68e99c2d3e6facf403fd464c77e5244b7766be", "generation_seconds_batch": 17.941024234052747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03529657423496246, "target_z": -0.4023437372030891, "ce": 6.38797664642334, "genuineness": 4.595211505889893, "identity": 0.6648470759391785, "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_Jealousy_and_Envy/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "064cfde8988bc57e5568f178a069dbe9a71432734cdb455de5b0d239fe77b326", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b12f16d37703e2978658dde1eac85b2ab9ce34cbc178fcf8bcf34fa8786142f1", "generation_seconds_batch": 25.06428135605529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.7524979710578918, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/064cfde8988bc57e5568f178a069dbe9a71432734cdb455de5b0d239fe77b326.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "06537fc2a1a8c352bb9a09cd5ee17f8155b96e41f60eebd03791dcaa232e4d96", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3c44c13d47b4a21d1643970451ac756081a2a72fc275fd2854adc95c55e02a48", "generation_seconds_batch": 19.244287997018546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.034743785858154, "genuineness": 4.243753433227539, "identity": 0.5917501449584961, "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_Jealousy_and_Envy/06537fc2a1a8c352bb9a09cd5ee17f8155b96e41f60eebd03791dcaa232e4d96.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "06d1b6e5400bba5b94726c7667e8d5c53bd8c2c5107a80847a1f4534d1b46140", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ce1a2d9663f47106df3db84859211ebd12f9012ad27a9751a8007ea476b10249", "generation_seconds_batch": 23.943315548007376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.5436887741088867, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/06d1b6e5400bba5b94726c7667e8d5c53bd8c2c5107a80847a1f4534d1b46140.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "08a1e28eca76f06791f2f4a2d63a60ac6a028af3a4e756a2cc361025525a93c3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b3f13512f1ff86e9faffecdd856bc8812ea7fbabaeb3f7ff38db0660591cd179", "generation_seconds_batch": 25.495244815014303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.863759994506836, "genuineness": 4.557555198669434, "identity": 0.6983433365821838, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/08a1e28eca76f06791f2f4a2d63a60ac6a028af3a4e756a2cc361025525a93c3.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "0907b43a9db56f976573042ffa095011b2a4780da5c8a29b559904d972a1fecc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3bc2e0ee88bc21aa0d16494d63dac07a72cc1d15b175883da7c80e94d9c0202c", "generation_seconds_batch": 25.375466553028673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 5.6254801750183105, "genuineness": 4.243753433227539, "identity": 0.5970370173454285, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0907b43a9db56f976573042ffa095011b2a4780da5c8a29b559904d972a1fecc.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "091ae378787b40afbfd6210394180264a70a8aa0fa9bedbace56a3b014eba9ef", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cb7ef13b59f0b423c7e971a8ee279740205a4fc4a63c7072ebec5f35d5d07fd9", "generation_seconds_batch": 23.814177980995737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.213237762451172, "genuineness": 4.243753433227539, "identity": 0.3479588031768799, "hypothesis": "The 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_Jealousy_and_Envy/091ae378787b40afbfd6210394180264a70a8aa0fa9bedbace56a3b014eba9ef.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "09d7e1caae54ca02107cf440e50b526ff0dd8fcb037c76373796dbc75260ceda", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e7e74f848885b508f5bb82d1748569f1833d63c5fc9f40a01773b9ff0f3cb59d", "generation_seconds_batch": 25.131123370025307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027460947632789612, "target_z": -0.419921866512253, "ce": 5.240260601043701, "genuineness": 4.507347106933594, "identity": 0.6561194658279419, "hypothesis": "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_Jealousy_and_Envy/09d7e1caae54ca02107cf440e50b526ff0dd8fcb037c76373796dbc75260ceda.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "09d927c8f2792c82b638bcd81ed318c865a117226250b0bc443f4c42da711d95", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "74729b5b705a444facd5306ca57e135506c36cd483b601bd9d2b88ce0f93e5cd", "generation_seconds_batch": 25.77280287106987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.2767791748046875, "genuineness": 4.557555198669434, "identity": 0.6809916496276855, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/09d927c8f2792c82b638bcd81ed318c865a117226250b0bc443f4c42da711d95.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "09ef65f7be9345975a1b134e925f6e31119e770fa0a03636c2162166b014c666", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dd8c9e49653b8c7027bf8b081b25d53ef1691451700291971d24a382b14fe620", "generation_seconds_batch": 19.512237248010933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02216467261314392, "target_z": -0.5312499853749589, "ce": 5.982900142669678, "genuineness": 4.65797233581543, "identity": 0.8091272711753845, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/09ef65f7be9345975a1b134e925f6e31119e770fa0a03636c2162166b014c666.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "0a9b3d5d5b848caa39b20f8efec64b9224017fcb863d34d4723234557894b956", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6fc82af7cd2574fb0186c37da9453df21ba273e355af6b39cc0143d7feb9e9b4", "generation_seconds_batch": 25.834864537930116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.0146708488464355, "genuineness": 4.331617832183838, "identity": 0.6838685274124146, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wien 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_Jealousy_and_Envy/0a9b3d5d5b848caa39b20f8efec64b9224017fcb863d34d4723234557894b956.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "0abcd5013d69a4ed13de6c8e18a49ef5b3d492643c30eb4201cfc104bbdf5f58", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4ec2a8c065637ca3690fdca3bd9623601df4f82e19f02061a28fe4b5b94bf34f", "generation_seconds_batch": 25.92302719608415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 4.971202373504639, "genuineness": 4.080576419830322, "identity": 0.32976463437080383, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0abcd5013d69a4ed13de6c8e18a49ef5b3d492643c30eb4201cfc104bbdf5f58.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": "0b5636af2c74ff9e6038b1b4495849f2e116d9eb476b62f3182b75a5ce33969a", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "1b849eab0b27c8e778b9c60bdee30b2ab1a00ad70cb6b01f4b9e64d999a5c85b", "generation_seconds_batch": 18.381049003917724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 5.919358730316162, "genuineness": 4.444586753845215, "identity": 0.42157551646232605, "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_Jealousy_and_Envy/0b5636af2c74ff9e6038b1b4495849f2e116d9eb476b62f3182b75a5ce33969a.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "0ba30ad469352c09944bfcec276eb209f2f98284e10908e80a1a7448e25b0330", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c2549ea629f33ba248f27b8cd0ca66d033447c659ce210fb6ac9c62c83e5ee78", "generation_seconds_batch": 24.171800701064058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.395919322967529, "genuineness": 4.281409740447998, "identity": 0.7129420638084412, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0ba30ad469352c09944bfcec276eb209f2f98284e10908e80a1a7448e25b0330.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "0ba5e6898d1e75300affaddea2dc8f5fc12e6deca804507a1dc5d8e7c9db6758", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "900b1a3c6dc823236da2f77aeacf57be5203d84754f9a610d4abc16c570a1085", "generation_seconds_batch": 29.87926796497777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 5.816103935241699, "genuineness": 4.507347106933594, "identity": 0.5970297455787659, "hypothesis": "De deur 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_Jealousy_and_Envy/0ba5e6898d1e75300affaddea2dc8f5fc12e6deca804507a1dc5d8e7c9db6758.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "0bbfb79a3e5a092021bd62a6aa60b83f6e99aaab7b6029a7f4121bad148d4515", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "26ec7bf4939df5e62e236d0c7d497b1200c412905d0462162a99a9fb6c910ffa", "generation_seconds_batch": 26.603089168085717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.252951145172119, "genuineness": 3.9173994064331055, "identity": 0.22818970680236816, "hypothesis": "The 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_Jealousy_and_Envy/0bbfb79a3e5a092021bd62a6aa60b83f6e99aaab7b6029a7f4121bad148d4515.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "0bcd8af3b14cc3033c18ab431592bb2f7dbfd22f8168b4e8e27c0fcfc2aefab0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3fa1845bab0c8130698e4b737de1082359464ddf5cc3921e7ac71cb02e2589fd", "generation_seconds_batch": 25.375458125956357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.816103935241699, "genuineness": 4.519899368286133, "identity": 0.737078070640564, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0bcd8af3b14cc3033c18ab431592bb2f7dbfd22f8168b4e8e27c0fcfc2aefab0.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "0c6e27b799c45ad47d56f0382d7aa62e4668fd5550ab8b1230811b515c879208", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b347d9276845ab02ce74c58b2d466c1b14f4369ba99a7493f03589ad80018d3f", "generation_seconds_batch": 24.942226220970042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.252951145172119, "genuineness": 4.607763767242432, "identity": 0.4610169529914856, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0c6e27b799c45ad47d56f0382d7aa62e4668fd5550ab8b1230811b515c879208.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "0c6eb506940f1c5c7342f71444ab9f75bf329ef0effbcb59758c0447ac03393a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2493ba210f9471c68bb7cad2728ea5b1602c43d82949f322b29f61f7de1b6a9f", "generation_seconds_batch": 25.170651655993424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.221180438995361, "genuineness": 4.193545341491699, "identity": 0.36716681718826294, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0c6eb506940f1c5c7342f71444ab9f75bf329ef0effbcb59758c0447ac03393a.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "0caeab716f08f40e42dad1c2fb2ea6ad37374cb14184fab3a8cd9825b7a28a68", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c08dd70773f8dc87d4e3355dcdf76b6719800ccf275b305741f3a5656a82a460", "generation_seconds_batch": 26.526089192018844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.09409761428833, "genuineness": 4.293961524963379, "identity": 0.5916827917098999, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0caeab716f08f40e42dad1c2fb2ea6ad37374cb14184fab3a8cd9825b7a28a68.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "93278eaa6a1d25550eae8ac0d650cce41b104ae9a1b585c6b2f2a2ac2e8ad773", "generation_seconds_batch": 20.82914017001167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 5.974957466125488, "genuineness": 4.20609712600708, "identity": 0.7133888006210327, "hypothesis": "Schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "0de83bbb0b5631fdab5a610470d41f34d7594b661640bb49a16bb920f31ecbda", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a7f38c322fbe4be5fae12d5d938d0450a478d57b1b0b0c86e54ceea50201c454", "generation_seconds_batch": 24.395631816936657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.070269584655762, "genuineness": 3.9801597595214844, "identity": 0.5381913185119629, "hypothesis": "The 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_Jealousy_and_Envy/0de83bbb0b5631fdab5a610470d41f34d7594b661640bb49a16bb920f31ecbda.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "0df80d3c0f5f30a666e2052be7b58a27cf026ed61bfd72ca57bd298d54d29dbb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "030be3f68df43880a111e014077686448be8647e14b1e0e8cc0cc4ed937c0ca5", "generation_seconds_batch": 23.026315969065763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.006728172302246, "genuineness": 4.2249250411987305, "identity": 0.4872530400753021, "hypothesis": "Ik heb het wel 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_Jealousy_and_Envy/0df80d3c0f5f30a666e2052be7b58a27cf026ed61bfd72ca57bd298d54d29dbb.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": "0e0e2a42f59d982ede52e04cdc73b761a31ed22fa2c8773650627af54d4f237b", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "e1ed4c1b50a7ac3729ff9ee77f199957768b5c5c1946fbe35ab474dbb7dad892", "generation_seconds_batch": 18.444944615010172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04313218593597412, "target_z": -0.38476564132259045, "ce": 5.959072113037109, "genuineness": 4.808597087860107, "identity": 0.7270975708961487, "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_Jealousy_and_Envy/0e0e2a42f59d982ede52e04cdc73b761a31ed22fa2c8773650627af54d4f237b.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "0e200f2ccba5f19a202303a6ba901f10bbd8263626652251b30e7c5db0370321", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "96b8f9e5b97245051e21ada9c09e618f000f5c2f0fad4f4a6b291ed05ff73ee5", "generation_seconds_batch": 25.109759100945666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.054384231567383, "genuineness": 4.281409740447998, "identity": 0.8179941177368164, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0e200f2ccba5f19a202303a6ba901f10bbd8263626652251b30e7c5db0370321.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "0e2c69ac274d6890f042946e703a5c1e6b2efa9b85938c7b268e160d615245f1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3c6a20707aa47e8eae1c34554f73b78e4b51d4c47e8ec9f17ff5856b8767b83e", "generation_seconds_batch": 26.353192933951505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03007282316684723, "target_z": -0.41406249007586504, "ce": 5.903473377227783, "genuineness": 4.356721878051758, "identity": 0.6746435165405273, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0e2c69ac274d6890f042946e703a5c1e6b2efa9b85938c7b268e160d615245f1.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "0f5ae681ce527dda488f4df3e6beb581d91b8d9b8cfbbc91814a6fff5f5cde21", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3ef91e5dbf4aaf091a6ac2b41c18f1e2f82bcd0b4590c5c038299ca23be324c1", "generation_seconds_batch": 27.25079905707389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.0305562019348145, "genuineness": 4.306513786315918, "identity": 0.655397355556488, "hypothesis": "De deur 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_Jealousy_and_Envy/0f5ae681ce527dda488f4df3e6beb581d91b8d9b8cfbbc91814a6fff5f5cde21.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "0fabf0aee7d07955c002d71ebb3893a6659fba5d0e5e6600aa18a162fe5a5a7c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "315d3a8a9ffd91739cf04adbb030790425f577571b2d2969aa11f06c6c6c00f9", "generation_seconds_batch": 19.156855802983046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.324435234069824, "genuineness": 4.65797233581543, "identity": 0.6077706813812256, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/0fabf0aee7d07955c002d71ebb3893a6659fba5d0e5e6600aa18a162fe5a5a7c.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "102da8f924b5237ee68615ad5258eff63dc11dabcef8ab8c972bc275434216f6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "142c2e53a576b538fe98ec0d75b692486b4a5536f25e90e008cb074a9890fad9", "generation_seconds_batch": 24.093321786029264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.157639026641846, "genuineness": 4.425758361816406, "identity": 0.5839696526527405, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/102da8f924b5237ee68615ad5258eff63dc11dabcef8ab8c972bc275434216f6.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "1050967693315edcbcd9e34fb976cabec88dc31fa8a81bd60fe3eb31e4ef001f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1f58f1eb6b15ae154754b63978e1ec63d41e0d1b43b5626af992f47904605173", "generation_seconds_batch": 22.183799137943424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.038498878479004, "genuineness": 4.595211505889893, "identity": 0.6996588706970215, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1050967693315edcbcd9e34fb976cabec88dc31fa8a81bd60fe3eb31e4ef001f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "10671e9a452dca96813ac8a059d315fc51b188723176ce96b2ac3a5fdb5a1043", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e979cd031f55e5a7d09301c50aadf3d9f2cbb932b82faab82a21ea86bacf5e2a", "generation_seconds_batch": 26.163546808063984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.5982876420021057, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/10671e9a452dca96813ac8a059d315fc51b188723176ce96b2ac3a5fdb5a1043.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "1097589a2d40c6e8ebebe39e14255a1c22c91ca7bcadd57d3099ac1fda9fc27e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1f6d230345fa5b8e574684fd6f3a272cac8db6ab63f14907abed07d62ec03910", "generation_seconds_batch": 26.196036829031073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.284721851348877, "genuineness": 4.218649387359619, "identity": 0.42971184849739075, "hypothesis": "The 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_Jealousy_and_Envy/1097589a2d40c6e8ebebe39e14255a1c22c91ca7bcadd57d3099ac1fda9fc27e.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "10cfceef3edbf5a81421390f4afc30f3674a93ad6097eb339cf3236bc7be99a5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "edb1c4e7cb40f4546dc2e3df6fa20f898345f69e52a68d770faa1a7053095229", "generation_seconds_batch": 23.943315548007376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.24500846862793, "genuineness": 4.6705241203308105, "identity": 0.618497371673584, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/10cfceef3edbf5a81421390f4afc30f3674a93ad6097eb339cf3236bc7be99a5.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "111a86c4b97434d31dc50077ec347917948abcc43d30b9e454448614438d1598", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bcdc22dd6a4fa1bb6916a3db9bc81e999858e6fd6ceda046a0ac2db541845c2a", "generation_seconds_batch": 25.028834199067205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.871703147888184, "genuineness": 4.406930446624756, "identity": 0.44683414697647095, "hypothesis": "De deur 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_Jealousy_and_Envy/111a86c4b97434d31dc50077ec347917948abcc43d30b9e454448614438d1598.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "1141c95ed87b81308ffb176f24550fcc959b07eb15ce2e6a48f7e0a899e65d1b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2a0bc799e694f3f208d23f033dabe21dcbdec0fbee6d61e99c60422697f164d3", "generation_seconds_batch": 25.910008443985134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.332377910614014, "genuineness": 4.306513786315918, "identity": 0.519740104675293, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1141c95ed87b81308ffb176f24550fcc959b07eb15ce2e6a48f7e0a899e65d1b.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "11e9372e25c8c47c5f346dce76b53dc10d8877bf5936d81188fd4c5eb1d914c4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "80a2c6cadf0ff70b698488b3429a8948cda4570bc66cef94876e6f16a7b0e812", "generation_seconds_batch": 26.26309426804073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 5.871703147888184, "genuineness": 4.582659721374512, "identity": 0.7850713729858398, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/11e9372e25c8c47c5f346dce76b53dc10d8877bf5936d81188fd4c5eb1d914c4.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "129b206f447786475f8753c03621b186abd3a50762ba0b3fb2fb3b7fc6acf052", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "72e083a3979b2628669a567793c7d3457221bf5939f4b942eef1e1f0b15a3300", "generation_seconds_batch": 25.605951708974317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 5.982900142669678, "genuineness": 4.532451152801514, "identity": 0.7945339679718018, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/129b206f447786475f8753c03621b186abd3a50762ba0b3fb2fb3b7fc6acf052.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "2d913b1f297dfa413e7d6eedb05fb8c0151727acaed257598f3d8c91007e5ffd", "generation_seconds_batch": 19.68660956202075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.316492557525635, "genuineness": 4.331617832183838, "identity": 0.5979694128036499, "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_Jealousy_and_Envy/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.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": "138e1f36bb81064b621abfd4887be4e0f8ba2609959cf744170000418bafb6ad", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I wrote the number on the envelope.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "672cc30d0cc88f4a1642e8b845429b90a77b325cf42398b827578c24f272a601", "generation_seconds_batch": 19.083271424053237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.316492557525635, "genuineness": 4.293961524963379, "identity": 0.36785686016082764, "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_Jealousy_and_Envy/138e1f36bb81064b621abfd4887be4e0f8ba2609959cf744170000418bafb6ad.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "139675f6fffeb56fa2734e86bf497f66bf22ec74483b227713006c683bd496c0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ff779d57ef18bb5daabe886de62791c5ef7a021cc283fce8f2a23426929ba87", "generation_seconds_batch": 24.61580934689846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.109982967376709, "genuineness": 3.9927117824554443, "identity": 0.32840079069137573, "hypothesis": "The 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_Jealousy_and_Envy/139675f6fffeb56fa2734e86bf497f66bf22ec74483b227713006c683bd496c0.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "142de51cf2e9bf7a9727e67acb336a435956f290d3e8d4fd1b18343dc05067fa", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0456273d91d1ca8de77f8d3c92cc99e63aee7809799b8970f55913b66fb80528", "generation_seconds_batch": 23.01861143996939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.696964263916016, "genuineness": 4.419482707977295, "identity": 0.4091854393482208, "hypothesis": "The 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_Jealousy_and_Envy/142de51cf2e9bf7a9727e67acb336a435956f290d3e8d4fd1b18343dc05067fa.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": "14769746d3ded627a8179ddc087af51a15c250b945c3ef48483be0151a59e92e", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I wrote the number on the envelope.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "7f06679d8266bf27295e12b70503e68213317612018ffbc048b8bf9f55ea443b", "generation_seconds_batch": 19.083271424053237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.213237762451172, "genuineness": 4.218649387359619, "identity": 0.39014920592308044, "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_Jealousy_and_Envy/14769746d3ded627a8179ddc087af51a15c250b945c3ef48483be0151a59e92e.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": "1489ed9dd2b1e329cdf89ea921f6fbaad7514f9bd82c773daeb534714828ad1f", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "422fb43c2e7fb7c3e3bca8176730c83cc15b3d346706cf982c3d1a28d2d55761", "generation_seconds_batch": 25.11631801200565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.824047088623047, "genuineness": 4.432034492492676, "identity": 0.7069252133369446, "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_Jealousy_and_Envy/1489ed9dd2b1e329cdf89ea921f6fbaad7514f9bd82c773daeb534714828ad1f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "148f4e5b701fa7b70570408212ba962f1aed9a48719e3ee8b52c0ee72282aa78", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3889863cfddc6d9486cb210893162b4941e6a0ec61722410441db8ab46a63113", "generation_seconds_batch": 24.790520512964576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.062326908111572, "genuineness": 4.846253395080566, "identity": 0.8479729294776917, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/148f4e5b701fa7b70570408212ba962f1aed9a48719e3ee8b52c0ee72282aa78.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "7c9494058c8e618d2edc69e046e43f019b96e1af887d4c5cc20ab8b07ba72717", "generation_seconds_batch": 18.469482885091566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01868218183517456, "target_z": -0.5234375057455518, "ce": 6.1894097328186035, "genuineness": 4.256305694580078, "identity": 0.463432252407074, "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_Jealousy_and_Envy/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "15b408f77ae70329a0fa90591c7331e3ea606c9b14f956da2bab8c061cf45100", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d5b81615f08f90d3651eee33cd5b8af42d6c817f618334700da567f228cb9389", "generation_seconds_batch": 24.714601119980216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.165581703186035, "genuineness": 4.883909225463867, "identity": 0.6428459882736206, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/15b408f77ae70329a0fa90591c7331e3ea606c9b14f956da2bab8c061cf45100.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "15e8e46542374e87f27b1bab7654e0c6d08da81e57342ecefdf98a4d60444ae5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fd3497ef6cc8f6a857797ea5eae81d6b41870127c3f681179054e8eea782c75d", "generation_seconds_batch": 29.818743888055906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.1894097328186035, "genuineness": 4.821148872375488, "identity": 0.6165767312049866, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/15e8e46542374e87f27b1bab7654e0c6d08da81e57342ecefdf98a4d60444ae5.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "16046fff1710b32d502aa33445a3e1f0206f6009e73a59048ad23566c080f8ac", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0a0f0aa557efeb5f107c4b560bfa783c61c8ce1c5107dae59eb419ca1316b395", "generation_seconds_batch": 25.705223979079165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 6.24500846862793, "genuineness": 4.381826400756836, "identity": 0.21499864757061005, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/16046fff1710b32d502aa33445a3e1f0206f6009e73a59048ad23566c080f8ac.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "169cbba1e3d6c65da53ae96bdb838d109c07ad7a7e224dff9ef085c006a1b14f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aaa39818a9e6376218543115b2464dc81185f61e7810c92e3e6da65403361075", "generation_seconds_batch": 23.814177980995737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.2571437954902649, "hypothesis": "The 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_Jealousy_and_Envy/169cbba1e3d6c65da53ae96bdb838d109c07ad7a7e224dff9ef085c006a1b14f.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": "16c95170711a070a3418634815ea52f64d98b322781f9aac4df8befdbe2f5eb0", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a7217f8fc57d178de72b3d58715b7d3dfc914d67ffd2e3ef4c42c346c2c93f88", "generation_seconds_batch": 18.970201210002415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.6340843439102173, "hypothesis": "De sleutels liggen op de kooktafel. Ikek in de la en daarna naast het raam neem ze mee als je weggaat.", "wer": 0.13636363636363635, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/16c95170711a070a3418634815ea52f64d98b322781f9aac4df8befdbe2f5eb0.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "191629ffbcaf412f1d75672762c37851079a86b48c307430aab07ccc5004bf77", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f4de4aeb98627bec96be3b7978e6f4e6ec4189a59aaa41567a0564eef319640e", "generation_seconds_batch": 25.265861809952185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 5.967014789581299, "genuineness": 4.519899368286133, "identity": 0.26910126209259033, "hypothesis": "The 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_Jealousy_and_Envy/191629ffbcaf412f1d75672762c37851079a86b48c307430aab07ccc5004bf77.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "197eb33daf713e91a4944419d2020733796dff3d5fc8c53f75ad39ad1f1b900f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d1fa203f1d29f388eb0d601a456dec34899a3f58bda5f04d2a59cecd4c4971b0", "generation_seconds_batch": 26.142955491086468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.125868320465088, "genuineness": 4.369274139404297, "identity": 0.7269097566604614, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/197eb33daf713e91a4944419d2020733796dff3d5fc8c53f75ad39ad1f1b900f.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "19c665b7b068dd16d42da10d04bf183c9e16114eceb56f4fc0630f482523338c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "55b79ba8e49109f265b8ba341777fef99ac8d1cb4ffec234ef22799d2e73daf2", "generation_seconds_batch": 23.934082203079015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.213237762451172, "genuineness": 4.582659721374512, "identity": 0.6543360948562622, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/19c665b7b068dd16d42da10d04bf183c9e16114eceb56f4fc0630f482523338c.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "19e8d56aa262968d618f1f5c7fd0612c6090b9367e6a1707fca3bc8778208001", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "35533e4201a8ab8569466853dc2b0d12b9bca338f9d953563a3d8e489db25772", "generation_seconds_batch": 23.97182786196936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.911416053771973, "genuineness": 4.306513786315918, "identity": 0.30850428342819214, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/19e8d56aa262968d618f1f5c7fd0612c6090b9367e6a1707fca3bc8778208001.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "1aae71f87708971c6ba1f9579dd5445e9d51168593f7689c5db83c2b4f0e652e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6efc1c2656dd994ed3a227188191eb483156799358ad3ba93776369acd015506", "generation_seconds_batch": 18.70319957600441, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.6275584697723389, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1aae71f87708971c6ba1f9579dd5445e9d51168593f7689c5db83c2b4f0e652e.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "1ad1864c5584c584224ca1e9f963dcbbabc274aa4f8659880687ec02948c45be", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e9cdc62174957c1072d27a62e098994131e27c71517f3a854c2effca99f35f6e", "generation_seconds_batch": 17.97622206294909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 6.078212261199951, "genuineness": 4.557555198669434, "identity": 0.6367355585098267, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1ad1864c5584c584224ca1e9f963dcbbabc274aa4f8659880687ec02948c45be.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": "1b8e6c5d30f745765992546c7dce8881ab1639f96e77cead2e90c2625b31c42d", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "429525725439e30b307a246dc8950b6d52c7f1717f3f562ffb4874ab0ed32d3f", "generation_seconds_batch": 18.992745368974283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.748591423034668, "genuineness": 4.607763767242432, "identity": 0.48784101009368896, "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_Jealousy_and_Envy/1b8e6c5d30f745765992546c7dce8881ab1639f96e77cead2e90c2625b31c42d.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "1ca80ad5d038bae1606e7f31ad919411cba0aea3afa99630a7f47ae3f6ab36c0", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "23c62d310c8a605bc09e229b7795cdee6c7e2232f829ae0afa761e6352357ac3", "generation_seconds_batch": 17.790779095957987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015199676156044006, "target_z": -0.5156249926874795, "ce": 6.268836498260498, "genuineness": 3.998987913131714, "identity": 0.6164734363555908, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1ca80ad5d038bae1606e7f31ad919411cba0aea3afa99630a7f47ae3f6ab36c0.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "1cff40f9a0863fa3620d5590a72af9519362ce3ffc8acaea40fd808f5bcd0cc9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "56f73be52c6e21688499fde9b97496ed674bdab45b405f3426e71718818915bb", "generation_seconds_batch": 25.821169184986502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.332377910614014, "genuineness": 4.231201171875, "identity": 0.5402167439460754, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1cff40f9a0863fa3620d5590a72af9519362ce3ffc8acaea40fd808f5bcd0cc9.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "5f92ce8b92de67a635b4586a0138fd9d117798d538edb10bb276222d50570ded", "generation_seconds_batch": 16.868185319006443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01868218183517456, "target_z": -0.5234375057455518, "ce": 6.149696350097656, "genuineness": 4.15588903427124, "identity": 0.5155330896377563, "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_Jealousy_and_Envy/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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "8fa9abb75d8a2ef9aa9b2d81ca19d9d53af99a92937f215295919331f3f16808", "generation_seconds_batch": 17.60779893491417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.3641486167907715, "genuineness": 4.457139015197754, "identity": 0.6067236661911011, "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_Jealousy_and_Envy/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "1ddfbbb8aa6febf13de5bf7d73a1d44740f913567dd70e858ab5f6140ee21bab", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1a2f11b34a4218887abafe7633156063aba10a47536ffd30ac3e17bf065bdf1a", "generation_seconds_batch": 25.400460949982516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025719687342643738, "target_z": -0.4238281397556217, "ce": 6.252951145172119, "genuineness": 4.419482707977295, "identity": 0.7300177812576294, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1ddfbbb8aa6febf13de5bf7d73a1d44740f913567dd70e858ab5f6140ee21bab.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "1e6d4e0bbcbd469a3a27e5ba71d9560fa8f6c8cf85ae9147d81f70d179df1438", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ae9fda09c3334aace38754f67b4cf9054baf589dc1b09d77ae570c0322ea1445", "generation_seconds_batch": 24.1138914990006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025719687342643738, "target_z": -0.4238281397556217, "ce": 5.95112943649292, "genuineness": 4.557555198669434, "identity": 0.22374564409255981, "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_Jealousy_and_Envy/1e6d4e0bbcbd469a3a27e5ba71d9560fa8f6c8cf85ae9147d81f70d179df1438.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "4ed283fc910b32dda87cf55ed442b41ba1ba6016f807e2446c8a2b3329d0ea62", "generation_seconds_batch": 16.868185319006443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.034353435039520264, "target_z": -0.5585937643638795, "ce": 6.260893821716309, "genuineness": 4.507347106933594, "identity": 0.6801322102546692, "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_Jealousy_and_Envy/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "1ebf0eb8763d435cd566d7d784fa22da6b615da95b056ffda16686ab145ee465", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "081a093d939cf911c4f76effdfa92c21994f889e18c26ca415ebf15aa2c22e93", "generation_seconds_batch": 25.15482202998828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.27834904193878174, "hypothesis": "De deur 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_Jealousy_and_Envy/1ebf0eb8763d435cd566d7d784fa22da6b615da95b056ffda16686ab145ee465.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "1ed74a0c004b509e70ae06169d97cd6a888499e95a42628b99e8bc3eedaeea13", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cc0f6f581770a9bc5ddaab338f07804e2adac01ac93632924b16527d37030432", "generation_seconds_batch": 19.91898058494553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.205295085906982, "genuineness": 4.7458367347717285, "identity": 0.5772691965103149, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1ed74a0c004b509e70ae06169d97cd6a888499e95a42628b99e8bc3eedaeea13.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "1efd4d61368e153644b73fc36b368a1c60250861b68cd257e00b0532a7827ffd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a2621d5bff778a43d7f02653e69e86cea8fba3ff2290388383dbcd5df3cd11a9", "generation_seconds_batch": 25.375466553028673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.704906940460205, "genuineness": 4.293961524963379, "identity": 0.6080018281936646, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1efd4d61368e153644b73fc36b368a1c60250861b68cd257e00b0532a7827ffd.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "1f2e02e7e1f2ed5826482fb9657e800d6faaaa66bb537fb71c16a647e067a4ef", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a65e91cf67ebec5eed4928e36b3096e9e6637a5f9c0a3dd9aebfa791ab427337", "generation_seconds_batch": 29.085697395028546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.260893821716309, "genuineness": 4.093128204345703, "identity": 0.42961376905441284, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/1f2e02e7e1f2ed5826482fb9657e800d6faaaa66bb537fb71c16a647e067a4ef.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": "1f3634d4f57b39c5806858ca95498274671431a88234f88c5004c33ace2c3ed2", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "30ea314c34c35bb88e46637c495968f75da729b395c9a0875ed69779c9bec027", "generation_seconds_batch": 18.381049003917724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 5.804190158843994, "genuineness": 4.545003414154053, "identity": 0.5707608461380005, "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_Jealousy_and_Envy/1f3634d4f57b39c5806858ca95498274671431a88234f88c5004c33ace2c3ed2.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "1f5fb86d3d9b85bc9f83bbc85aed95aadfc7f83fa00cb5ab4225a38030950871", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a86b786a1a023aedf53e474a11827fb0075d759b7f48f012db9c9fb1185a4e3c", "generation_seconds_batch": 30.06650677707512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.070269584655762, "genuineness": 4.482243061065674, "identity": 0.5992472171783447, "hypothesis": "De deur 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_Jealousy_and_Envy/1f5fb86d3d9b85bc9f83bbc85aed95aadfc7f83fa00cb5ab4225a38030950871.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "20004ef5cf452a4b7227dc5cf8138d29309c44a7889f0b1705ea32dd8c92b505", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "771d2eaf8e6fa08d5d94c1cc291528a3fa69b957c7939ba6665723423659eef6", "generation_seconds_batch": 25.222252093954012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.5173141956329346, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/20004ef5cf452a4b7227dc5cf8138d29309c44a7889f0b1705ea32dd8c92b505.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "208cd29906c35cf013c5039dba084196dbd01d5322529a1df160fab966080486", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d11fa4333259453bf7955d7d6dc8ba9338b769ff70afae9f4a9ca6fc8d65c6e6", "generation_seconds_batch": 25.765534614911303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03181406855583191, "target_z": -0.4101562502611614, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.32273387908935547, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/208cd29906c35cf013c5039dba084196dbd01d5322529a1df160fab966080486.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "209482e8c8f97fb4f670b2c3646d27d5bae4403e1c2e332c393762e26141c347", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "91213bc48a570fafe0a0f6c1416f4eebd887229ec0ef183a155c4f6b034d90ea", "generation_seconds_batch": 26.087353318929672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.205295085906982, "genuineness": 4.65797233581543, "identity": 0.7723727226257324, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/209482e8c8f97fb4f670b2c3646d27d5bae4403e1c2e332c393762e26141c347.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "20b048dbfea4a00bbe82cad26d068261cc07abaf25106d72b17b70910cb09c11", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e37d8ed857db5e843c3ac1b6c6b34f8995f16c8ac9fb587b27435b4a6f076c39", "generation_seconds_batch": 18.87741148704663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.062326908111572, "genuineness": 4.381826400756836, "identity": 0.5158907175064087, "hypothesis": "De deur 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_Jealousy_and_Envy/20b048dbfea4a00bbe82cad26d068261cc07abaf25106d72b17b70910cb09c11.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "20d12377a208af3076e74093d8c478274751ab99c6eaf8f21b4a5c488537ddb9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8e57fc333b343a8d8c738364f9d20f72fe3a43da5b0db3d39dee2131ec180315", "generation_seconds_batch": 26.087353318929672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.990842819213867, "genuineness": 4.137060642242432, "identity": 0.8311115503311157, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/20d12377a208af3076e74093d8c478274751ab99c6eaf8f21b4a5c488537ddb9.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "211fbd1735bb4ed4c958ba93f31f2947b1a56f075e6a59d608206958108cb187", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b69e0d82cd679e2e19f61d1854a481d139ea190d724b7e95660b7f969ae76dc2", "generation_seconds_batch": 25.11427977506537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.197352409362793, "genuineness": 3.860914945602417, "identity": 0.38913846015930176, "hypothesis": "The 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_Jealousy_and_Envy/211fbd1735bb4ed4c958ba93f31f2947b1a56f075e6a59d608206958108cb187.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "219ac13ed80506a6be91105070ce5af6932c5b94df6683a3ee47cd30e14ec7a9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e6e8c1e77c6c9e8cc7315c4e574fc64fd71076610deda87a690ebce97d03cfd2", "generation_seconds_batch": 26.335930843022652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.3641486167907715, "genuineness": 4.7081804275512695, "identity": 0.5929895639419556, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/219ac13ed80506a6be91105070ce5af6932c5b94df6683a3ee47cd30e14ec7a9.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "21b4e58abdcf5ccd3a3500d1298e5540291c79775e454e6a964c146206debdbc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4cfa90c2f658006c2640f1e66a66e15fe523ecba11c325a1468ba0f60bbde706", "generation_seconds_batch": 27.66135234606918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.427689552307129, "genuineness": 4.1998209953308105, "identity": 0.6232115626335144, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/21b4e58abdcf5ccd3a3500d1298e5540291c79775e454e6a964c146206debdbc.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "21eb36d3061d470fa65ee072b7341398ed51a84feb7c519e4579aa9bf41dd7d9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "57ca867dae6ce38589683698ff071a8a939f0498b84cddbda698b8d13596b759", "generation_seconds_batch": 18.605538545991294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.109982967376709, "genuineness": 4.582659721374512, "identity": 0.6607159376144409, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/21eb36d3061d470fa65ee072b7341398ed51a84feb7c519e4579aa9bf41dd7d9.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": "233ca8e88ad3d40600a757d28bdf8f98f9bc38d6f1b630630e32057ab133c423", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f57f6523f9530bc0515f7a181e5489d37dbd3cff2841211d48f857ec5af91749", "generation_seconds_batch": 21.036978077958338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 5.982900142669678, "genuineness": 4.344170093536377, "identity": 0.5771032571792603, "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_Jealousy_and_Envy/233ca8e88ad3d40600a757d28bdf8f98f9bc38d6f1b630630e32057ab133c423.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "238fccde095a2d21688bac423c466f15da40d1494a0c03a989025685d60a9d71", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5517702fec9a315feb5e06af0873a1c04f1557bff21826dc351c70a29a006daf", "generation_seconds_batch": 24.816020054975525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.356205940246582, "genuineness": 4.457139015197754, "identity": 0.34016597270965576, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/238fccde095a2d21688bac423c466f15da40d1494a0c03a989025685d60a9d71.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": "23aea405017c9d7021911764cc2dce3aab79ea4b509a99d63ab4824ed3342364", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "29b38eb653ece5a40cff65de02fee0d05516d1273cc0f68f4916435ef85c2346", "generation_seconds_batch": 18.992745368974283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.7684478759765625, "genuineness": 4.6203155517578125, "identity": 0.6544381380081177, "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_Jealousy_and_Envy/23aea405017c9d7021911764cc2dce3aab79ea4b509a99d63ab4824ed3342364.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "23b0ceaaeca161c198e8cf308da2d59d09af9d98297481b3a1115f81c62ec998", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "42714ee97bdbc640d5c61e135310b0286be53f796985c63070bad50ce395ca41", "generation_seconds_batch": 25.40307593799662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.0305562019348145, "genuineness": 4.381826400756836, "identity": 0.6633932590484619, "hypothesis": "J'ai trouvé ma 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_Jealousy_and_Envy/23b0ceaaeca161c198e8cf308da2d59d09af9d98297481b3a1115f81c62ec998.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "23c8947da294caadaf690b8063ce994e37000579763ec073a818e4924d995f5c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2786818d477ecbc40f0af034947e3e261a7bfc241fd505a2b4d5eaf50e075da5", "generation_seconds_batch": 24.25494969205465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.967014789581299, "genuineness": 4.582659721374512, "identity": 0.7277717590332031, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/23c8947da294caadaf690b8063ce994e37000579763ec073a818e4924d995f5c.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "2401b02499ec9a6a56c320e3da119d2e2a1423550da8396275a4864fb98ce9d0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6e7ee5b026a3e369e3a818f93c8940a4849ba38465a4bd2454ef0d38cf2647f0", "generation_seconds_batch": 24.98443908803165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.879645347595215, "genuineness": 4.231201171875, "identity": 0.6503853797912598, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2401b02499ec9a6a56c320e3da119d2e2a1423550da8396275a4864fb98ce9d0.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "25055cf0bf47bd4e392e2267d0121239f5c25355049ac33861b04cfb5a2a1547", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "83b3ba211df6336f4711a80081d142b0b931e22f9c84b13aa1de1b15418d7ab9", "generation_seconds_batch": 24.49768776795827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.967014789581299, "genuineness": 4.494794845581055, "identity": 0.504472553730011, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/25055cf0bf47bd4e392e2267d0121239f5c25355049ac33861b04cfb5a2a1547.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "25288801666822262750f4dbb3b795ebf81aa54f2f2975008d52725e256bfac7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b682512e1eb4b27362591c9a322109d14a14ce7e247638d2904e58f49080b849", "generation_seconds_batch": 24.816020054975525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.3641486167907715, "genuineness": 4.406930446624756, "identity": 0.37466657161712646, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/25288801666822262750f4dbb3b795ebf81aa54f2f2975008d52725e256bfac7.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "25d69f9041cd5f5cf94add878de2dc6d87f4c7051df3fbbb53b4f7b1c533787b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "420e18b1987fbb871c3fb5cee5c7467f1829e8eec794ccf1814b0ce17dce937e", "generation_seconds_batch": 18.202773513970897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 6.205295085906982, "genuineness": 4.13078498840332, "identity": 0.3660699129104614, "hypothesis": "The 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_Jealousy_and_Envy/25d69f9041cd5f5cf94add878de2dc6d87f4c7051df3fbbb53b4f7b1c533787b.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "26476cfa040728059cc57d34b3035bebc138b62cccf4752a9ae3de180073ec79", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "667c0ae8f334c12bc2607b9b775a879f9c928b1b531c68030bbdf51cfce3c6a3", "generation_seconds_batch": 27.97268780192826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.919358730316162, "genuineness": 4.394378662109375, "identity": 0.6442207098007202, "hypothesis": "De deur 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_Jealousy_and_Envy/26476cfa040728059cc57d34b3035bebc138b62cccf4752a9ae3de180073ec79.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "7987b9c7d1752e37509da9a9bb6bb755c0b2407e0c88420f76dcedf40befc514", "generation_seconds_batch": 17.553626246983185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015199676156044006, "target_z": -0.5156249926874795, "ce": 6.395919322967529, "genuineness": 4.18099308013916, "identity": 0.13031832873821259, "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_Jealousy_and_Envy/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "27af0c0fe3112f1bf5cadeb1c72e1f78553d478100fae8cccb1106554c96a143", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d9631ce7413b5f58764694e7d6668a1159253cc08b3c176654e8aac527ce3298", "generation_seconds_batch": 26.096314931986853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.268836498260498, "genuineness": 4.432034492492676, "identity": 0.3296978175640106, "hypothesis": "The 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_Jealousy_and_Envy/27af0c0fe3112f1bf5cadeb1c72e1f78553d478100fae8cccb1106554c96a143.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "2802095c9d1fc66da3070a9ae405d6531d7fc1da9d0465e360a7e54b91b8b82e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "23d6c6a32bfb6a153a5265e3fa202293dbd3d89fb7495677b2a4c71fd054ace2", "generation_seconds_batch": 18.76660830504261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 5.871703147888184, "genuineness": 4.381826400756836, "identity": 0.7386429309844971, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2802095c9d1fc66da3070a9ae405d6531d7fc1da9d0465e360a7e54b91b8b82e.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "283907b1244cd64b0f8c8e8144e1c88e7f1d9629d035aa5939cb7723f04e95d8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ad06d49d6161a212d2676713c5128beb4e945f207a2150217f0b457bd080616f", "generation_seconds_batch": 19.03412283596117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 5.4825119972229, "genuineness": 4.017816066741943, "identity": 0.7840571403503418, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/283907b1244cd64b0f8c8e8144e1c88e7f1d9629d035aa5939cb7723f04e95d8.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "286d53af389e206e69cf31d1647ec45639fd102398780f32dc9d25b81d4f10eb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e3037d6c4f68956cd2f4df426b382ba4acba903999a6b00fcba67e06f0a3da1f", "generation_seconds_batch": 25.647474114084616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.086154937744141, "genuineness": 4.532451152801514, "identity": 0.5186583399772644, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/286d53af389e206e69cf31d1647ec45639fd102398780f32dc9d25b81d4f10eb.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "28b7c49840c9550e5cad2b8c7ae787d180474fc95551edd8d8330229e08dd62c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3c493f7b94f59f86f8694039b36dfe9ad453d0d5a8e92a40fb1fd32370d02882", "generation_seconds_batch": 18.218161099008285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03007282316684723, "target_z": -0.41406249007586504, "ce": 6.09409761428833, "genuineness": 4.720732688903809, "identity": 0.8300358057022095, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/28b7c49840c9550e5cad2b8c7ae787d180474fc95551edd8d8330229e08dd62c.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "28cd30a3c8e675b944b3b37a4dbd7d5652b9f79f0dba7209df6a42d44ec63d2c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "81a08264f9c503b6776e7afe9b4d5fe2e27683989bb71af60cd81edca1c1f73d", "generation_seconds_batch": 25.21281693293713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005622804164886475, "target_z": -0.49414062356361205, "ce": 5.6413655281066895, "genuineness": 4.287685871124268, "identity": 0.6932358741760254, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/28cd30a3c8e675b944b3b37a4dbd7d5652b9f79f0dba7209df6a42d44ec63d2c.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "2bf06969145d0900e281caa23bb4e6a47f5ab58c9e1a3c6ae2b68e01d6fe9d2d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "01020d7da57960f08433b442268a7a1fdbb061016ffc2cd37845d5c4fe13deb8", "generation_seconds_batch": 26.213524178951047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.80021858215332, "genuineness": 4.570107460021973, "identity": 0.6455970406532288, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2bf06969145d0900e281caa23bb4e6a47f5ab58c9e1a3c6ae2b68e01d6fe9d2d.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": "2c1e493b252d5f9f136ed39c5c837fcb831d4b64e0f3fe10ed6200b67668800f", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "391a793cd9c4414c38f11d0fe84f46955b47c8b9a2a5cccd108ad072962baca7", "generation_seconds_batch": 23.2767468780512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 5.621508598327637, "genuineness": 4.394378662109375, "identity": 0.7760502099990845, "hypothesis": "La route tourne à gauche après l'autre pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2c1e493b252d5f9f136ed39c5c837fcb831d4b64e0f3fe10ed6200b67668800f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "2d18ea752dc771d9cc276a4db4ad3c5405a7e02550fd20ec50ffb61f80ea1828", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1cb1e50835adf544b743b6f3769a5f77a7c7caffdb07ddf538d52a6419cbfc0b", "generation_seconds_batch": 19.007442898931913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.078212261199951, "genuineness": 4.7458367347717285, "identity": 0.7167050838470459, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2d18ea752dc771d9cc276a4db4ad3c5405a7e02550fd20ec50ffb61f80ea1828.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "2d1db8755fd645575ab7343153cdca6d7b7c9e4ecbf65baaaa42eec7e434c4a6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e56c5f84f0e8e12b7ed628d74ede1c2fc93f5555e15421e7b8a3d6c5c88566f2", "generation_seconds_batch": 25.488854003022425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03007282316684723, "target_z": -0.41406249007586504, "ce": 6.038498878479004, "genuineness": 4.482243061065674, "identity": 0.5227158665657043, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2d1db8755fd645575ab7343153cdca6d7b7c9e4ecbf65baaaa42eec7e434c4a6.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "2d4a16d938681539deac82c9a35b55823a2086b62bb229fc9ef7359060a5ce1b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a7bad76960b8058fd35a80054f62ae8da075a6b4722520c5f3efc4e94da4e7e5", "generation_seconds_batch": 21.885866347001866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 5.863759994506836, "genuineness": 4.507347106933594, "identity": 0.6549351215362549, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2d4a16d938681539deac82c9a35b55823a2086b62bb229fc9ef7359060a5ce1b.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "2db4fe4bc59cf62a998416d71b1d7b4960cbd18df3e4ef7483392dbe40a86de7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c292832c7f6cf285274db9f58232576b376ea53d294e7c0d0e74e42828bc4165", "generation_seconds_batch": 25.441644023987465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.022613525390625, "genuineness": 4.68307638168335, "identity": 0.8357598781585693, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2db4fe4bc59cf62a998416d71b1d7b4960cbd18df3e4ef7483392dbe40a86de7.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "2e945ae409cd827c27b3a46ef609324bc7ec2b8c5305e8b377d61450752755a2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "06a3005196e8ce5860acb3cbb1323a04f162a959a7f03aa53cdbb8ebcad336a8", "generation_seconds_batch": 25.216213528066874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 6.1894097328186035, "genuineness": 4.2751336097717285, "identity": 0.44610750675201416, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2e945ae409cd827c27b3a46ef609324bc7ec2b8c5305e8b377d61450752755a2.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "2e9cc3d6c4ce4d5b5a7275f596dadd985753a3db276f7485478c9e824991c4dc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24a213e44a5a748464ae14e629a656c266a85829808071e8f71ddc616d9fba9b", "generation_seconds_batch": 25.829414322040975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.006728172302246, "genuineness": 4.042920112609863, "identity": 0.388056218624115, "hypothesis": "The 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_Jealousy_and_Envy/2e9cc3d6c4ce4d5b5a7275f596dadd985753a3db276f7485478c9e824991c4dc.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "2ed7649fcece85346467b19ac4591b4204428682900b4ff8d69258b8f159336a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ab0c9eed0a91de5df119c4acebe7a4d389ec95859064bb224807bd9e644c409b", "generation_seconds_batch": 27.139840487972833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.982900142669678, "genuineness": 4.3127899169921875, "identity": 0.726290762424469, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2ed7649fcece85346467b19ac4591b4204428682900b4ff8d69258b8f159336a.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "2edb9ffb54bacdfc6f6ebfb57f3482eca4942be1e03f076b277a7022a9ef5621", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e0122c8a506c8121db73a4d0aa3c3c7fa3fd270c13ac2e352808ad99e9b1bba8", "generation_seconds_batch": 18.86279111704789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.998785495758057, "genuineness": 4.6956281661987305, "identity": 0.7034231424331665, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2edb9ffb54bacdfc6f6ebfb57f3482eca4942be1e03f076b277a7022a9ef5621.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "2f3e5e9356b405ac17dd0a5f3f15aa44db4357e9c126d899fc48babcaf932873", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e10904dff89b9ff2f81c144e2fba6c20d6beb9df520b7e2e1cce53deee08ff65", "generation_seconds_batch": 19.82128885993734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038779065012931824, "target_z": -0.39453125757368196, "ce": 5.665193557739258, "genuineness": 4.595211505889893, "identity": 0.7214464545249939, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantre 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_Jealousy_and_Envy/2f3e5e9356b405ac17dd0a5f3f15aa44db4357e9c126d899fc48babcaf932873.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": "2f793f5505b89d8e7b1424d6d225e728110550b6135433afa186408840416839", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "433ec3221391d35d888cc2d6c2790cbe2c8c044502964baabd30a75a775ab0c2", "generation_seconds_batch": 23.39611007005442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.95112943649292, "genuineness": 4.7458367347717285, "identity": 0.7130100727081299, "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_Jealousy_and_Envy/2f793f5505b89d8e7b1424d6d225e728110550b6135433afa186408840416839.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "2f800557cc82ee28e10ccc28ac4b7cb10535cef1d77efdd1da1d66986e0279b9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2d4ba78589487d33b27bd6a84acb3cf5cdcfa4c5b933c85cc4344f3b6f918896", "generation_seconds_batch": 24.781120319035836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.0146708488464355, "genuineness": 4.337893962860107, "identity": 0.5946280360221863, "hypothesis": "De deur 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_Jealousy_and_Envy/2f800557cc82ee28e10ccc28ac4b7cb10535cef1d77efdd1da1d66986e0279b9.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "2f82575ab4728fdb2b1f0cf0336ef4402829f35b783410f203c42b2564758c66", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f46e53ef10eb827828e519e8c2b0b09534f1d1eb7ada350a2635d52e596b544f", "generation_seconds_batch": 24.14670153800398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 5.911416053771973, "genuineness": 3.961331605911255, "identity": 0.3832124173641205, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/2f82575ab4728fdb2b1f0cf0336ef4402829f35b783410f203c42b2564758c66.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "302cf872bf18d8153078a0f8f01790fa2683d900356d44e33a6c25778d7760c9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c27339a0713444dda1e0282763e28d5b75d032a6f1018815491f65a8647352e0", "generation_seconds_batch": 25.854997836984694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.09409761428833, "genuineness": 4.369274139404297, "identity": 0.7287750244140625, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/302cf872bf18d8153078a0f8f01790fa2683d900356d44e33a6c25778d7760c9.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "315db80b730568a89d88a4eae4c2d13a473decfd8dcab36c38762795ccf705ca", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "40a70566f9f84f2d4aea2449fe32e3790c7dffaa9e64f75929d09d89052cad9d", "generation_seconds_batch": 25.92302719608415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.184661865234375, "genuineness": 4.482243061065674, "identity": 0.7419028878211975, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/315db80b730568a89d88a4eae4c2d13a473decfd8dcab36c38762795ccf705ca.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": "3278fb9021803d232033b7c379aed0040215497e68a161cd7a896be432997597", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "bafd991ff67b9acd773a290d212b572a3159e72fb3c3db4fb6fd9817e79d8681", "generation_seconds_batch": 21.57722077902872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 6.141753673553467, "genuineness": 4.68307638168335, "identity": 0.7260148525238037, "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_Jealousy_and_Envy/3278fb9021803d232033b7c379aed0040215497e68a161cd7a896be432997597.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "328dbbf82a85e68d1804411bf973764e10ef7c5f3dfba3e5c631c984d16ea26f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "34bd8b0b76d0e3570e98007ad65549dc5661332ff5b3ca3e5cd21518b4fbe47e", "generation_seconds_batch": 23.182550720055588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.871703147888184, "genuineness": 4.419482707977295, "identity": 0.7848869562149048, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/328dbbf82a85e68d1804411bf973764e10ef7c5f3dfba3e5c631c984d16ea26f.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "335a77ffa8698de4b6127fc91cae008b455a894f1e569844fed8a412348a5341", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fdbe1231b2a10cecc966639184f6b6bd3e1cc8e13667107a1e84c531ae6d196b", "generation_seconds_batch": 19.66635363304522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.5241093635559082, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/335a77ffa8698de4b6127fc91cae008b455a894f1e569844fed8a412348a5341.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "3e9646f360f2cae3ace23ed89c32188aaeb878e2a7e16547619812c4a26a5d7e", "generation_seconds_batch": 17.997399386949837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 6.125868320465088, "genuineness": 4.3881025314331055, "identity": 0.6199133396148682, "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_Jealousy_and_Envy/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "34197ffeb03f2d49da9c620f51edcc3c6beff5e56a9fd4aca0616ec8ec49d85c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b2e2f4205198a0b2d43b95910e7d90576206c0be3782200dd0df261c374a4f35", "generation_seconds_batch": 23.194389638025314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.268836498260498, "genuineness": 4.7081804275512695, "identity": 0.5123185515403748, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/34197ffeb03f2d49da9c620f51edcc3c6beff5e56a9fd4aca0616ec8ec49d85c.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "3455f188f83278a443c8c8e0d4c9ca0797e7a15beb9a123bef2651358c74143b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4ad169b83beb84ea376d34edde8afd4b0f18de650e413df2ac19a5802d4c125c", "generation_seconds_batch": 18.6099129000213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 6.149696350097656, "genuineness": 4.645420074462891, "identity": 0.7142311334609985, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3455f188f83278a443c8c8e0d4c9ca0797e7a15beb9a123bef2651358c74143b.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "3464f6ff1db7a0f65b62cbe22d8b482ac55fc431bbafdf4562f762f04589fc09", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2bac7eff24fa8a735a534fc5c2f9541e164339cb0783b03a82df60fe27ff005c", "generation_seconds_batch": 25.473619619035162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032684698700904846, "target_z": -0.40820311363947703, "ce": 6.078212261199951, "genuineness": 4.758388519287109, "identity": 0.7477673888206482, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3464f6ff1db7a0f65b62cbe22d8b482ac55fc431bbafdf4562f762f04589fc09.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "65dd67d1708be498aa2653cfda76b7799a4cf1f9ceb3292251acf5b1b2271292", "generation_seconds_batch": 23.559094437980093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.459460258483887, "genuineness": 4.149612903594971, "identity": 0.3507975935935974, "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_Jealousy_and_Envy/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "3500e65f6ad774832f8dd386c4d4998175498a53f7de50290febeae85cdaad57", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33ed2dc9e0f890211d9461db0aff3364793c17fbed619f823705d76e0c7aa443", "generation_seconds_batch": 17.96815433294978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.133810997009277, "genuineness": 4.6705241203308105, "identity": 0.6314952373504639, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3500e65f6ad774832f8dd386c4d4998175498a53f7de50290febeae85cdaad57.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "350cdb8df1605b068f92886e0d9a1ca85921a9119a06d81b40543312ee40cffd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e42a3be3de707fca249003440050223c9c4caa6da06e274c6f150848c2df6712", "generation_seconds_batch": 24.395631816936657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.292664527893066, "genuineness": 4.105680465698242, "identity": 0.26132720708847046, "hypothesis": "The 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_Jealousy_and_Envy/350cdb8df1605b068f92886e0d9a1ca85921a9119a06d81b40543312ee40cffd.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "354b35db7d5ec6e92c72915859848b9032bc4885eed3a61f22be60d722eca74a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "209f0fdbc805a90f5c9f6ae131bff30b641a6d3cc0c50b57c8a786aab9901502", "generation_seconds_batch": 22.666620434029028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007364049553871155, "target_z": -0.4980468633783156, "ce": 5.561938762664795, "genuineness": 4.218649387359619, "identity": 0.8878600597381592, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/354b35db7d5ec6e92c72915859848b9032bc4885eed3a61f22be60d722eca74a.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": "35b2b184d4087451a658fd8bb295a9a90fe6ef4e1cb072a1672c3c815f179a25", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "cf777d5095a555daeada6099a085dd83f167602c519ff703b312955b8d2f1fb9", "generation_seconds_batch": 19.034643503953703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 5.534139156341553, "genuineness": 4.570107460021973, "identity": 0.8205792903900146, "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_Jealousy_and_Envy/35b2b184d4087451a658fd8bb295a9a90fe6ef4e1cb072a1672c3c815f179a25.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "35cde1756f66a333be01e8bf3ce269d220062a759abcaf8fc0e8d7c109f0d169", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "99771133934fb4e8786a5975a504b5c92c90f9fea0eea2b95fbe042a8676040a", "generation_seconds_batch": 24.69084544898942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 5.808161735534668, "genuineness": 4.344170093536377, "identity": 0.621173083782196, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/35cde1756f66a333be01e8bf3ce269d220062a759abcaf8fc0e8d7c109f0d169.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": "36cb23bff385655b3ec919892c82f82b1f4f90c7bf7f7d45be2e3b1e2e638cf3", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Escribí el número en el sobre.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eefb12121783a506503b26b90ee4d39083d86bf92c0e1e89884a9bd415c47b6b", "generation_seconds_batch": 26.550525714992546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 5.7128496170043945, "genuineness": 4.545003414154053, "identity": 0.6265153884887695, "hypothesis": "Escribe el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/36cb23bff385655b3ec919892c82f82b1f4f90c7bf7f7d45be2e3b1e2e638cf3.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "371875ac23716f48afedfe7355bb0e57452ac020dfc4028ca979bdd58b690f18", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7e08c995698baaa285b56edd89d1c6e2942af0cc58bb072ca5ba92b382f69391", "generation_seconds_batch": 17.78251366096083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.3641486167907715, "genuineness": 4.469690799713135, "identity": 0.36303454637527466, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/371875ac23716f48afedfe7355bb0e57452ac020dfc4028ca979bdd58b690f18.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "374111674378daa6fa8d477648674114d41fc728ea47f153429d96d60520e582", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b50d1e8029f895df96989d99af5c0920ad0fadbcd967c73f66d45fa380f202f8", "generation_seconds_batch": 21.090732053969987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.6083932518959045, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/374111674378daa6fa8d477648674114d41fc728ea47f153429d96d60520e582.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "37be7d40314bf89199921b25692df442e94a218d3a51db87ebdcaf422d2c319e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "319192b72787a867a1dab4c5771cc4ebc8f3aa52b7a9dfe8d8f6b2c1bb4181d1", "generation_seconds_batch": 25.80492114997469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.125868320465088, "genuineness": 4.268857479095459, "identity": 0.6843312978744507, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreiben.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/37be7d40314bf89199921b25692df442e94a218d3a51db87ebdcaf422d2c319e.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "38239ee9793d29598e5947567aab5e387cb05f710d8c2b4d0ca98400129034dc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eea0eefd93f5aa89ab14ba128bcaf7700b65167c262e3994baaf552b1ee9a232", "generation_seconds_batch": 24.89510673901532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 6.443574905395508, "genuineness": 4.444586753845215, "identity": 0.28713876008987427, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/38239ee9793d29598e5947567aab5e387cb05f710d8c2b4d0ca98400129034dc.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "383e374d7a90d7e4b6d32cc4e7d002dda2556e286235d8453230d5a08dbde415", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dda3b8c109a39b5fbf2696b138b8374e54912d7ccc0307395f56ea2c2f650bda", "generation_seconds_batch": 24.286725113983266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.24500846862793, "genuineness": 4.632867813110352, "identity": 0.5411583185195923, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/383e374d7a90d7e4b6d32cc4e7d002dda2556e286235d8453230d5a08dbde415.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "3848fa3a504486114a515bacf11b5aea2cbb4eb7a1e80e0c8ba9104b64208a53", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "290ec5f0f7b5e0cade6a84f6293bbfceaee0b6672069c847ee21fb94f3dae7c4", "generation_seconds_batch": 25.36387553298846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.205295085906982, "genuineness": 4.444586753845215, "identity": 0.3186147212982178, "hypothesis": "The 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_Jealousy_and_Envy/3848fa3a504486114a515bacf11b5aea2cbb4eb7a1e80e0c8ba9104b64208a53.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": "3851a208e0431fb2d2898cd0848f710f7e6e5f1be178d576a8b9dd41489571d6", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "013872208b5466bdf2f6e0ca7f3c8a956b33239e19c6b96598b81e6ac0bba966", "generation_seconds_batch": 25.795815675053746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.0146708488464355, "genuineness": 4.457139015197754, "identity": 0.7711695432662964, "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_Jealousy_and_Envy/3851a208e0431fb2d2898cd0848f710f7e6e5f1be178d576a8b9dd41489571d6.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "38707fbf2cc98a2b6ec34995325f67da310ae35e72b25599c8e8d3a2e4804c44", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a74bb32a321b6c969979d7990f4996ccdf753a4ef2597a8e520ad9783d9bfb7f", "generation_seconds_batch": 26.342265640036203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.6399701833724976, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/38707fbf2cc98a2b6ec34995325f67da310ae35e72b25599c8e8d3a2e4804c44.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "38ea88f10b0fa4399980ed49901bc47bf35a27bee63c29fad2f10f065519d34a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6c6367c80555e765afcb25710c034ea2755cea8a25c77d58ab4e4026c5fa2b71", "generation_seconds_batch": 28.602911591995507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.665193557739258, "genuineness": 4.595211505889893, "identity": 0.670575737953186, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/38ea88f10b0fa4399980ed49901bc47bf35a27bee63c29fad2f10f065519d34a.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "397dfa7e209619ab23b46ef0591ee949bddea6dc34e5b21a66e35116c10d31b8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "edcafd78c9420f158af9472525dab2e5e12daea62c10eea6757d0d8d19ea9e12", "generation_seconds_batch": 22.18009858892765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.252951145172119, "genuineness": 4.168440818786621, "identity": 0.20241083204746246, "hypothesis": "The 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_Jealousy_and_Envy/397dfa7e209619ab23b46ef0591ee949bddea6dc34e5b21a66e35116c10d31b8.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "39e7f0576f1bdd36251b923b62222ba998c889baa0d1c56238778461ab2e3812", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a82dbcbfcdf789f0edff33483e5346a8d8338c1923b41b096b1174988f1a7c38", "generation_seconds_batch": 24.843744238023646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.403861999511719, "genuineness": 4.607763767242432, "identity": 0.25652623176574707, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/39e7f0576f1bdd36251b923b62222ba998c889baa0d1c56238778461ab2e3812.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "3a093c7d4e60bce8fc223931446cbe44f7a2aa1d5964a42b810d263ffae4c38a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "75fb350b6ad8d39a4a1ecda4fc37ffdcf0ad4d52d6a9008d8efcfc6b551c4a07", "generation_seconds_batch": 24.366160852950998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.7247633934021, "genuineness": 4.3881025314331055, "identity": 0.5635875463485718, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3a093c7d4e60bce8fc223931446cbe44f7a2aa1d5964a42b810d263ffae4c38a.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "3ab2a083195ec7d6e99d462673f900c6397d8328655ba76d5a257b816a5bc590", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "93937a4e6799d3fc5fb5e466c86acb9054c1a7679613a608248d36f86ebd3f38", "generation_seconds_batch": 19.92256663297303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.1020402908325195, "genuineness": 4.570107460021973, "identity": 0.6699196100234985, "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_Jealousy_and_Envy/3ab2a083195ec7d6e99d462673f900c6397d8328655ba76d5a257b816a5bc590.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "3b47560ecf4a2e5cbaabb40a2e3f832464d1c8090c6b62738b99dafea953dfb9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e92c086a559b2688f5f7da5c61c6bc8e8f8959ff93b3bb47b5f594a760934334", "generation_seconds_batch": 23.94664634799119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 5.9431867599487305, "genuineness": 4.331617832183838, "identity": 0.7373192310333252, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3b47560ecf4a2e5cbaabb40a2e3f832464d1c8090c6b62738b99dafea953dfb9.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "3b5ba4bf2313c54a2a960dbd41993fd1ac12fe1d3e5931ce4f1f9e06863bb9a8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cafa1ab08afbd58e93cd2847d53da7480db4486fc479ef07874092d7a35d7fdb", "generation_seconds_batch": 23.961409020936117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.3641486167907715, "genuineness": 4.519899368286133, "identity": 0.5442404747009277, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3b5ba4bf2313c54a2a960dbd41993fd1ac12fe1d3e5931ce4f1f9e06863bb9a8.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "3b6440d9865726d1f28ff65b1f0b443cae84c388f1a6f339b0710c6e20ec50b7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2305744940780557f31aa178c75bd47bc23e94132ca597742ea21704cbb9dbd0", "generation_seconds_batch": 24.14670153800398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.879645347595215, "genuineness": 4.105680465698242, "identity": 0.808076024055481, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3b6440d9865726d1f28ff65b1f0b443cae84c388f1a6f339b0710c6e20ec50b7.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "3b7a89bc2e1ebfed5b1f7c81b7ca06d424a0d5107de74245ba523362a47cdf2b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a81984c3f824faaf0da0622c2af7ff30533c97c08a6eb29834b1ee37a0c2b634", "generation_seconds_batch": 24.49768776795827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.788304805755615, "genuineness": 4.268857479095459, "identity": 0.8014588356018066, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3b7a89bc2e1ebfed5b1f7c81b7ca06d424a0d5107de74245ba523362a47cdf2b.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "3c4cbfc5b3839d728cb3ca7063c025c2d4107278fe1efb114a2141146fc32dc8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fd88b8acacacd3fbfbc923a44831b34ac8620a43662055604cef3efb8540bba5", "generation_seconds_batch": 23.96776816190686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.784333229064941, "genuineness": 4.319066047668457, "identity": 0.5433641672134399, "hypothesis": "De deur 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_Jealousy_and_Envy/3c4cbfc5b3839d728cb3ca7063c025c2d4107278fe1efb114a2141146fc32dc8.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "831bd9923d5e954ea7d7b3b9890aeeb67440236de9a0f7fab1b4127a105702b3", "generation_seconds_batch": 17.420003319042735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.181467056274414, "genuineness": 3.948779582977295, "identity": 0.7783530950546265, "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_Jealousy_and_Envy/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "3c7c2feb4c9119da66d42564a0d604c7641968115dad24ca1af56d55f0408832", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "464d83123656ed21d174f5cb4d1dc2a850232102de8befa1508e2ae90b5ea4d1", "generation_seconds_batch": 28.697127102059312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.18550416827201843, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3c7c2feb4c9119da66d42564a0d604c7641968115dad24ca1af56d55f0408832.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "3cfcd5a2fe162fa836c68ba8e579616101dc3ccb0d54fb10e7bee99827254c7a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2ca7054662d57848233a124b63a00ed7a79b12273aacc3a9bf6bfe468f50bbd9", "generation_seconds_batch": 24.743730827001855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 6.348263263702393, "genuineness": 4.080576419830322, "identity": 0.20348481833934784, "hypothesis": "The 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_Jealousy_and_Envy/3cfcd5a2fe162fa836c68ba8e579616101dc3ccb0d54fb10e7bee99827254c7a.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": "3d0518a324db910465c0a5fc0740eba9ff438ec9e094244ace95a9b302d3ba85", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "35d891d1538c1e3c38e6b6769a0a2e1aeafe931c3ee3299ca59d0639d33f650b", "generation_seconds_batch": 18.85864643007517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 5.839932441711426, "genuineness": 4.7332844734191895, "identity": 0.7212279438972473, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3d0518a324db910465c0a5fc0740eba9ff438ec9e094244ace95a9b302d3ba85.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "3d201ce3c079c918d01f3f26c31831343ccf9e567a4b01d4bc2095449fe67e1b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f4e3f51bdb3146f41f62481d9520bfd5719baab581c5dab79d41beade8e6bf78", "generation_seconds_batch": 25.23288531997241, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.340320587158203, "genuineness": 4.356721878051758, "identity": 0.38104456663131714, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3d201ce3c079c918d01f3f26c31831343ccf9e567a4b01d4bc2095449fe67e1b.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "3d7c2db815d1bd68dc290356eabc5f24941f5c952f3b4a8dc4b82733e2041e08", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0ff09001b32190e69dfe6d192d6f1744ffb50b018376507a4a4300dbf96fc25c", "generation_seconds_batch": 26.933353058993816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.5279766917228699, "hypothesis": "De deur 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_Jealousy_and_Envy/3d7c2db815d1bd68dc290356eabc5f24941f5c952f3b4a8dc4b82733e2041e08.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "3ddb2e6b5c01d29952a2d7c3e8250ae586d68ebc2e517ad5a811f5a773061108", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0d4bedcafef6245152749246a3eda9106a21eaaccf73b3d6857117b5ae1f7925", "generation_seconds_batch": 26.427332905004732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.125868320465088, "genuineness": 4.381826400756836, "identity": 0.2240007072687149, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3ddb2e6b5c01d29952a2d7c3e8250ae586d68ebc2e517ad5a811f5a773061108.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "3e635916b5fcdf2d52369e29356d742a57a4a94bb269a016685f1d7070c6fa29", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d2508583f6468c75ac9913a9944aa0cf22d75658cf4271acf370c295e14f932b", "generation_seconds_batch": 25.623565277899615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.0305562019348145, "genuineness": 4.457139015197754, "identity": 0.5195438861846924, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3e635916b5fcdf2d52369e29356d742a57a4a94bb269a016685f1d7070c6fa29.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "3e9e9173dc87776f8106bb307ccaa647afc5f9332bbee757de92c89137197540", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6ff5cd24da4b1e1d0d82da31968266ed14ea39ef2de17308d58ee8a392025a0c", "generation_seconds_batch": 23.026315969065763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 5.974957466125488, "genuineness": 4.231201171875, "identity": 0.6084764003753662, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3e9e9173dc87776f8106bb307ccaa647afc5f9332bbee757de92c89137197540.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "3f3a22571175f3d939885a61d5d2caad80379473bb45d9914cb5dd57f14fe349", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7ef307c4b83a2f93794a2f1cb664e7a5e490022cdbb66683c08a582a874205f8", "generation_seconds_batch": 24.714601119980216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.022613525390625, "genuineness": 4.7081804275512695, "identity": 0.8043813705444336, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3f3a22571175f3d939885a61d5d2caad80379473bb45d9914cb5dd57f14fe349.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "3f58bd02ce8e357b23a0e16248665cddce822cf89417fb0fe7a513929e4d8f4f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "57e084ea9c9f30f8021986a4912680fe5435ba9babc75b7ff1182374f8216cec", "generation_seconds_batch": 25.611332962056622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.038498878479004, "genuineness": 4.557555198669434, "identity": 0.6923544406890869, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3f58bd02ce8e357b23a0e16248665cddce822cf89417fb0fe7a513929e4d8f4f.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "3f5e972aad5beff0c8ce487a1adb316971086e1f39c33513998bd5478e8e29f3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a734166175b6c25ddffefdd6166f7cc97645ad1a2cbadcf7d3f91a9bbe56490a", "generation_seconds_batch": 25.623565277899615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.332377910614014, "genuineness": 4.406930446624756, "identity": 0.6078740358352661, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/3f5e972aad5beff0c8ce487a1adb316971086e1f39c33513998bd5478e8e29f3.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": "3f784f1c1327976ce006e0cd531b9bfd13494f5072372f4160a247f466915111", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a714da3d473068ed08e3eb2a3e29d9e7dcf3a0e100456b940ee1c74943f84f3", "generation_seconds_batch": 24.88898547796998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05009719729423523, "target_z": -0.36914061520644575, "ce": 5.911416053771973, "genuineness": 4.720732688903809, "identity": 0.6311100721359253, "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_Jealousy_and_Envy/3f784f1c1327976ce006e0cd531b9bfd13494f5072372f4160a247f466915111.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "406d56e377c32ea1961110b296c6d83983cd7d7e3cb45295c9002c2f5a3fd417", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "01a5534c3d5e83c9d145d23959478915397c9577eba69222132ef1282453ff39", "generation_seconds_batch": 26.142955491086468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.8875885009765625, "genuineness": 4.293961524963379, "identity": 0.6129494905471802, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/406d56e377c32ea1961110b296c6d83983cd7d7e3cb45295c9002c2f5a3fd417.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "4123979377599b57b8d06d2646f03010a4abda4fc68ce120276cd8fe0de78b21", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7779cc8dfae9149e7c39b12726234b018a386b86c894072697ff7d73349ee45d", "generation_seconds_batch": 17.97622206294909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 5.728734970092773, "genuineness": 4.65797233581543, "identity": 0.7351161241531372, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4123979377599b57b8d06d2646f03010a4abda4fc68ce120276cd8fe0de78b21.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "414a0d24d56609d9ed4ab0310d27cc22db25cf8dcddaaafee01e6fa300830d7d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ba036997ab62c1799830b34382d4c75b8b12c110d97132ea9e0667840d6562ee", "generation_seconds_batch": 24.61209334305022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.895530700683594, "genuineness": 4.532451152801514, "identity": 0.7254371643066406, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/414a0d24d56609d9ed4ab0310d27cc22db25cf8dcddaaafee01e6fa300830d7d.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "4179c43b29df9e0dfbd979adf8eb33e74354df34625cfb0aaa347a9dffd49df8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "931e2e46de52d618109b6f0719795c3a2eaa5433ead44c7c2b0a36362b8bba37", "generation_seconds_batch": 25.02018914790824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.982900142669678, "genuineness": 4.607763767242432, "identity": 0.6547068357467651, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4179c43b29df9e0dfbd979adf8eb33e74354df34625cfb0aaa347a9dffd49df8.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "41acd1041edcb28c5e48f964f16ec7fb342d9037780d417d10d40c021558cecb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b24a0b67bd0f7e9cdf309e78f491f8c1bffa9a761f3dbdf5fc267c7d75043e47", "generation_seconds_batch": 24.6161754950881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.133810997009277, "genuineness": 4.7081804275512695, "identity": 0.6079756617546082, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/41acd1041edcb28c5e48f964f16ec7fb342d9037780d417d10d40c021558cecb.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "41c94fb4d18e11f3471a6e8f020b3f83963719eb1a5870591dc01d9f4f302f3e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f87915d0763aa2fac8bcf12ee060ddf3e63a7ce89fcd813714d85143aa2a0e48", "generation_seconds_batch": 18.891782106948085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.48471197485923767, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/41c94fb4d18e11f3471a6e8f020b3f83963719eb1a5870591dc01d9f4f302f3e.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "4216f4ae97d31621e1c2b919872e281940f695028ddecd1c8281fb3a3d96125c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "890b334838b6574d7cc34c8a91f2c85f118b796d4f96a9909bf30c795630e2c8", "generation_seconds_batch": 25.35941005893983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005622804164886475, "target_z": -0.49414062356361205, "ce": 6.109982967376709, "genuineness": 4.356721878051758, "identity": 0.6729075312614441, "hypothesis": "De deur 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_Jealousy_and_Envy/4216f4ae97d31621e1c2b919872e281940f695028ddecd1c8281fb3a3d96125c.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "4282b56899e073d3d230578b3d330f82d50eb57cb000c7f993fb0b4e37e80175", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "40ec62320733f176bd6e4d2381d9c014c0cfb09c8d952c14da7f1ecaab7d65ef", "generation_seconds_batch": 25.522637429996394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 6.062326908111572, "genuineness": 4.256305694580078, "identity": 0.7126856446266174, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinfallen.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4282b56899e073d3d230578b3d330f82d50eb57cb000c7f993fb0b4e37e80175.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "42869b5760daa01e51e0c03c2ae056e38e03def00988e8aa0cea2a0028e8716b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "99398b44784da12bb1315050d7bde0103c2742c94e23d241e774dfb9b4e1f89b", "generation_seconds_batch": 26.342265640036203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.213237762451172, "genuineness": 4.3504462242126465, "identity": 0.7116867899894714, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/42869b5760daa01e51e0c03c2ae056e38e03def00988e8aa0cea2a0028e8716b.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "43057f202ae47624b5a0237e31ed02aec8408f8636740454cba2e9c2e2c5d72f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4b118f9d76072c1e4100ef58a9982bb79619e097a269002e261761630cdaed5d", "generation_seconds_batch": 18.240804973989725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.44134509563446045, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/43057f202ae47624b5a0237e31ed02aec8408f8636740454cba2e9c2e2c5d72f.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "ec1a8774fc0049057a2425af2a3aab46d738f5e886b7323714d64df1ca9d197f", "generation_seconds_batch": 17.997399386949837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.5521941184997559, "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_Jealousy_and_Envy/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "438aee5e9ca12ab6916196c1a5ca183839ebe06a1f6419687b43307112a20914", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f7a1e221ee26a98eab499f9944e77737abfe64c4377ec4cf26fd4bd1bdf25b45", "generation_seconds_batch": 24.044502418022603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 5.839932441711426, "genuineness": 4.256305694580078, "identity": 0.7336887717247009, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/438aee5e9ca12ab6916196c1a5ca183839ebe06a1f6419687b43307112a20914.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "005f046debfe8b1e025832a93b69d41869638d2fef9bff17ea330bd8928d3f6f", "generation_seconds_batch": 18.67256733297836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.268836498260498, "genuineness": 4.469690799713135, "identity": 0.5708308219909668, "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_Jealousy_and_Envy/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "440ad708527e62ed585e5780e8e8f3f9b82c510e1d669e657ac7ba075cc81d41", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3f4558ca87e0d1a93ae62c9a7e8e340e8830ea9b64d1cfd748a206c47d597153", "generation_seconds_batch": 25.0568349219393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 5.903473377227783, "genuineness": 4.281409740447998, "identity": 0.6242523193359375, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/440ad708527e62ed585e5780e8e8f3f9b82c510e1d669e657ac7ba075cc81d41.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": "441b75528f3bd6b8476ac03f4f4f0ec41e1bab21d08601a426675437b8d7dfbe", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3134b1628ce1aad438629257b60ee03d00386b635263f13dd9cedfc9c26078fa", "generation_seconds_batch": 26.19890572503209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.070269584655762, "genuineness": 4.457139015197754, "identity": 0.6428345441818237, "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_Jealousy_and_Envy/441b75528f3bd6b8476ac03f4f4f0ec41e1bab21d08601a426675437b8d7dfbe.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "441d955f1fe69eb32be0dd354625e8bd3a344aebf6436569d5e705cfb65d1384", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "82af7d2d56144c55b4eb0ca57d04bc1cc475d39c1e1ec8aa49e4dba42cf3ca32", "generation_seconds_batch": 18.53689101000782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027460947632789612, "target_z": -0.419921866512253, "ce": 5.919358730316162, "genuineness": 4.68307638168335, "identity": 0.671968936920166, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreiten.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/441d955f1fe69eb32be0dd354625e8bd3a344aebf6436569d5e705cfb65d1384.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "445b7318486653145c4076a815b04541144bc420b12db283d4888fafe2cdee69", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2e1552449162bd2dbaa0de598558b24f83d4b7b38923b3e121b47babfef2c9b8", "generation_seconds_batch": 18.76660830504261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.871703147888184, "genuineness": 4.457139015197754, "identity": 0.6980224251747131, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/445b7318486653145c4076a815b04541144bc420b12db283d4888fafe2cdee69.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "445e3ad2f5378875e24839797f82db158b410ff6ba3a31f86feda6fc94f21320", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "93878818b878674a92bd95e22c0d400a2113ea1554cc69c67211ffef4edb956f", "generation_seconds_batch": 24.743595986044966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.173524379730225, "genuineness": 4.325342178344727, "identity": 0.7309272289276123, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/445e3ad2f5378875e24839797f82db158b410ff6ba3a31f86feda6fc94f21320.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "44eaa35755f8d5c8e85705b5182c4aa25bb94ce5d9333c77f0f83fbc9838d5b6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d9ad50cb280e230f334126d05b42d2f9bc2acaeeb18a2666a799c95645b7524d", "generation_seconds_batch": 25.110205846023746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.419747352600098, "genuineness": 4.2249250411987305, "identity": 0.6104526519775391, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/44eaa35755f8d5c8e85705b5182c4aa25bb94ce5d9333c77f0f83fbc9838d5b6.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "45904c4e91e879b08d735529cd4dab7bb8e410ff2697c7494213f5c3c6036028", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46a3a0654d453fcf6e210d34602e5eeb38a5c6e3a5f94dc52a0ef26612044c54", "generation_seconds_batch": 19.678008171962574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.1894097328186035, "genuineness": 4.193545341491699, "identity": 0.09997250139713287, "hypothesis": "The 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_Jealousy_and_Envy/45904c4e91e879b08d735529cd4dab7bb8e410ff2697c7494213f5c3c6036028.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "44fb902e2314785678eda3599651d6bd2355135b0e48f2b70c7e6c6a72fb4088", "generation_seconds_batch": 17.845083377091214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 6.2767791748046875, "genuineness": 4.300237655639648, "identity": 0.6610446572303772, "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_Jealousy_and_Envy/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "46f5c805a9c28ff0367983d71c2df28935ee13b6a68971ad93d4acf63f8de167", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4c173b4014b94edec0f2aae50193065ae46be972e5f2ae2e65c778a407c49011", "generation_seconds_batch": 19.130602285964414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.855817794799805, "genuineness": 4.595211505889893, "identity": 0.79693204164505, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/46f5c805a9c28ff0367983d71c2df28935ee13b6a68971ad93d4acf63f8de167.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": "4767254708ddb52157dc1a563faa945ae34bcc33b784cbd1e4d2f846d6e482c1", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "dfce9ec0471714fcb2bf12c6baa5bd91cb304f8db32d8f3f3301f47a21edfef4", "generation_seconds_batch": 30.290494438959286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 5.967014789581299, "genuineness": 4.532451152801514, "identity": 0.6410256028175354, "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": 0.120000000000001, "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_Jealousy_and_Envy/4767254708ddb52157dc1a563faa945ae34bcc33b784cbd1e4d2f846d6e482c1.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "478e84e5970cb259ac9f0cb282d4dfbe19af6a9f8822b4eb1f743c505d961524", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6d1db5d7833efaed59337d7dac84bad4ee92aa34cf378b0ce95a921ca7752028", "generation_seconds_batch": 24.781120319035836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 5.816103935241699, "genuineness": 4.570107460021973, "identity": 0.42745864391326904, "hypothesis": "De deur 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_Jealousy_and_Envy/478e84e5970cb259ac9f0cb282d4dfbe19af6a9f8822b4eb1f743c505d961524.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "47cd86338fe08e90268e6375e6e5c7c173dbcb3623778a8bee75e6a0c55d30a9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "df77857abc520e4711b03f1673137cceea3e6b08fdefa94cb07cd7a859e6bdd5", "generation_seconds_batch": 27.139840487972833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.157639026641846, "genuineness": 4.425758361816406, "identity": 0.7751123905181885, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/47cd86338fe08e90268e6375e6e5c7c173dbcb3623778a8bee75e6a0c55d30a9.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "fdc41ef6d997f2a58d16f992a5dd0053d18cb32a174f6f390e393261655c2173", "generation_seconds_batch": 18.331307807005942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.7806909084320068, "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_Jealousy_and_Envy/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "48f216edaf619a31341e8dc8bb6216510df8b6340a4730bebd491096919b4181", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a00dae376390bfa46cef887dc910dfe3c22634052444f800be9c5744ab896ec4", "generation_seconds_batch": 25.164790660026483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.070269584655762, "genuineness": 4.482243061065674, "identity": 0.6222246289253235, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/48f216edaf619a31341e8dc8bb6216510df8b6340a4730bebd491096919b4181.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "4905509260915533ba1bf1fd07f6fb8b18870b4aebada0f6d967645d8cac2166", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fa1cbafceea77c299287a064b67230cf321f815b8b0287f090b2ac212eb5ea3f", "generation_seconds_batch": 25.45057526405435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.149696350097656, "genuineness": 4.055472373962402, "identity": 0.3248382806777954, "hypothesis": "The 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_Jealousy_and_Envy/4905509260915533ba1bf1fd07f6fb8b18870b4aebada0f6d967645d8cac2166.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": "4916d5a94895302c754242b0229af47d3f96e01522ab96501c9ce4ce3510c718", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fba3909d32af2bf16913b3a2df9ba31192edf7faebb48bc120f7e2b96caad7e", "generation_seconds_batch": 23.39611007005442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 5.764476776123047, "genuineness": 4.557555198669434, "identity": 0.7300669550895691, "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_Jealousy_and_Envy/4916d5a94895302c754242b0229af47d3f96e01522ab96501c9ce4ce3510c718.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "4933ad742f243460e26f32cb3da421fd4db812efc033658bc722f1a8b9bf1e81", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2975f25ef43b79ac274ba00f7004e1876de3e83616f64dcc512b736870d2a91d", "generation_seconds_batch": 19.810116045060568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.6336678862571716, "hypothesis": "De deur 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_Jealousy_and_Envy/4933ad742f243460e26f32cb3da421fd4db812efc033658bc722f1a8b9bf1e81.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "49517c83bf08dc6a38e9f4f939559ecef46486e05df5d3cc071418baaea10965", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a7203bd26a724b6bec5b88a092868d0e9d3da8b03bbe58a9028b89142e54e598", "generation_seconds_batch": 18.364206062979065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 6.53094482421875, "genuineness": 4.607763767242432, "identity": 0.3943018913269043, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/49517c83bf08dc6a38e9f4f939559ecef46486e05df5d3cc071418baaea10965.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": "49c5177ad3aec80c23453ff2610a584bf191d07883f37e08c8bd26c2d034c181", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a70ee229e82fcc4e180aac91d26ba348516ecfc1f4366615eb9b51fa630e601", "generation_seconds_batch": 25.840192414005287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 5.6532793045043945, "genuineness": 4.65797233581543, "identity": 0.8840062618255615, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-le bien et verifie les deux derniers chiffres. Appelle-moi quand tu aurais 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_Jealousy_and_Envy/49c5177ad3aec80c23453ff2610a584bf191d07883f37e08c8bd26c2d034c181.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "0615d85a40417f79ca160650bae3e41db0d06f8c59cc22445a64f4faa333f2fe", "generation_seconds_batch": 19.68660956202075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.173524379730225, "genuineness": 4.331617832183838, "identity": 0.6343644857406616, "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_Jealousy_and_Envy/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "4b06df0d77899d1a35f48649b646f947b9f9c001ef3e0c69dd2655840d68f305", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1b52e3d004bfe001bd42ba5687c79bae7b407eac7efefadb8419abd4297c885a", "generation_seconds_batch": 25.664753176039085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.23706579208374, "genuineness": 4.080576419830322, "identity": 0.4355623424053192, "hypothesis": "The 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_Jealousy_and_Envy/4b06df0d77899d1a35f48649b646f947b9f9c001ef3e0c69dd2655840d68f305.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": "4b8c75325d4521659627f10720b0c24e50e23836274c2b392119009a17a3f8d7", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "688b6a734e7d9a5b74eba71c9e9898a4a4ec0b0b45782fe09d8051622d6b26b9", "generation_seconds_batch": 20.77451357198879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.062326908111572, "genuineness": 4.645420074462891, "identity": 0.7015067934989929, "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_Jealousy_and_Envy/4b8c75325d4521659627f10720b0c24e50e23836274c2b392119009a17a3f8d7.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "4bd59273abda0810d5cdf183e6abbfbeb500467d7b90038ad6466d4bd2293b0e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "949cd7316483a8a17159ff94bd23dcec392091685c3feb38c3125f68a23a41a4", "generation_seconds_batch": 26.26309426804073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 5.704906940460205, "genuineness": 4.406930446624756, "identity": 0.6197960376739502, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "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_Jealousy_and_Envy/4bd59273abda0810d5cdf183e6abbfbeb500467d7b90038ad6466d4bd2293b0e.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": "4ce2810432af688dedade54f20c17191bfb60cc6bda7e86e4f3395c4879635c2", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36ff502ec8a44046926290afb8f3fc4c429359221c11bfb566abd09b1b29f2c7", "generation_seconds_batch": 18.902301168069243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 6.070269584655762, "genuineness": 4.720732688903809, "identity": 0.8899102807044983, "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_Jealousy_and_Envy/4ce2810432af688dedade54f20c17191bfb60cc6bda7e86e4f3395c4879635c2.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "4d7dc49b5d7d1b943147a526dd902af9a908e9a83ee03e4dd65820efa0600d80", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e1e09713a3f52bef1408c278e143fbe57814b6573c9428b5618fec8ed7860250", "generation_seconds_batch": 19.92256663297303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.5536775588989258, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4d7dc49b5d7d1b943147a526dd902af9a908e9a83ee03e4dd65820efa0600d80.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "4d7fb84255fbad5115d5003ea99db9aee54cb43676a5160f59dd30ea6ddb39c9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "40707a63ca39fd474ba2092b81e62d06c63b1fccc38bc11f73bfe43e05bb2ab4", "generation_seconds_batch": 23.33064280904364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 6.09409761428833, "genuineness": 4.595211505889893, "identity": 0.8016777634620667, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4d7fb84255fbad5115d5003ea99db9aee54cb43676a5160f59dd30ea6ddb39c9.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "4dcea46f2e48e581da62036ffffd28e32a6f4ab6cc0c5ec4ed2644e623dce1ac", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0fde0513e31fa6e4de55cac09039fa3eafc9a9b1d1c95aedb5256a6998f34271", "generation_seconds_batch": 27.585448164027184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.895530700683594, "genuineness": 4.469690799713135, "identity": 0.7012991905212402, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4dcea46f2e48e581da62036ffffd28e32a6f4ab6cc0c5ec4ed2644e623dce1ac.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "4e684e881adfd0c67759ab3cc2aa589df4c10122d8225488ae088d327be7b093", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "75c0398275187aff0d019612d87eba7fefcc5f07c5779c1ca8c539d8aee0613d", "generation_seconds_batch": 26.380755561054684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 5.359400749206543, "genuineness": 4.7332844734191895, "identity": 0.6309348344802856, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4e684e881adfd0c67759ab3cc2aa589df4c10122d8225488ae088d327be7b093.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "4f3af6f4195a25d7f33b7f0044165d3088eadb700cb052c3fa4a73a0ccda20f0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "473c02ffd2dc1034ecd29ae036a71a21428976282fb737c58d47b775a5743cc7", "generation_seconds_batch": 18.94928582198918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.8752621412277222, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4f3af6f4195a25d7f33b7f0044165d3088eadb700cb052c3fa4a73a0ccda20f0.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "4facff5377ca59acabb3f55fbfaafc3b3123545d1d2ed90f5b8cb13c188606e1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "04784cd982c5262800357a016caa8e17194a62786c314fef58907384d57c84c2", "generation_seconds_batch": 24.63604245998431, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 6.316492557525635, "genuineness": 4.6203155517578125, "identity": 0.38855254650115967, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/4facff5377ca59acabb3f55fbfaafc3b3123545d1d2ed90f5b8cb13c188606e1.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "504c589d050f599de06629cc739183f98cf3443d00ed55c200b0010852c7f3fb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8274371834b4818ef806a080f4ebe5f92397b4d6b8367a6927cbf5a31d76da29", "generation_seconds_batch": 24.281332539976574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.736677646636963, "genuineness": 4.369274139404297, "identity": 0.41375571489334106, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/504c589d050f599de06629cc739183f98cf3443d00ed55c200b0010852c7f3fb.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": "50524b3eeb91191d978be098f2b8da23d13ab76bae750fe7353308e24566c900", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "416318b8d504ae01688718e49a08305db789115a52038d92136352f96b35aac9", "generation_seconds_batch": 18.94835698103998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03964969515800476, "target_z": -0.39257812095199757, "ce": 6.0305562019348145, "genuineness": 4.68307638168335, "identity": 0.8713670969009399, "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_Jealousy_and_Envy/50524b3eeb91191d978be098f2b8da23d13ab76bae750fe7353308e24566c900.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "505c633480d14c31aca4cc71f48d36cb20ba7701b6768c130154eb8cd1260116", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "48ba3d0738b355856fabe2020a5be2ae509ab6994d9470125331fe281b217dc7", "generation_seconds_batch": 25.372179500060156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.959072113037109, "genuineness": 4.482243061065674, "identity": 0.7328343987464905, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/505c633480d14c31aca4cc71f48d36cb20ba7701b6768c130154eb8cd1260116.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "50e821c8c1aed9803a56e28caa1477830de5cf7fab93abe7cbe094216bed0c7f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c98e9a29d2aa8dc169a0189666c2845e0b070d4b698abf71462bd28aea928e66", "generation_seconds_batch": 22.18009858892765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.974957466125488, "genuineness": 4.331617832183838, "identity": 0.41968196630477905, "hypothesis": "The 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_Jealousy_and_Envy/50e821c8c1aed9803a56e28caa1477830de5cf7fab93abe7cbe094216bed0c7f.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": "512b1a9998b94798bc3fbf9d1aebe820f01a0224d6bcf1abd054435806391b42", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "64fa210647d188fe7d6a9bc759018914c79eff855bfcb38cb5dc8f24794bd4c7", "generation_seconds_batch": 25.11631801200565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.792276382446289, "genuineness": 4.507347106933594, "identity": 0.6605570316314697, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis, près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/512b1a9998b94798bc3fbf9d1aebe820f01a0224d6bcf1abd054435806391b42.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "5131c3a8fa130df1f181edd82a5edf0eadf6a226b57f688d685d55b05a1862c0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6d3c91b4796d4545709c6870bf93fdd32f544585cf6095165c2b8e287f756647", "generation_seconds_batch": 25.554383600014262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007364049553871155, "target_z": -0.4980468633783156, "ce": 6.165581703186035, "genuineness": 4.494794845581055, "identity": 0.24847358465194702, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5131c3a8fa130df1f181edd82a5edf0eadf6a226b57f688d685d55b05a1862c0.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "515300b9a58311806b3135800f4543b122845fcbba2d980ea22a178fba367ce1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0f2ae9d094dc7162622e9164d9bf96bd8f0c46c2488da80dc17bdb16d70f834c", "generation_seconds_batch": 25.022631751024164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.990842819213867, "genuineness": 4.7458367347717285, "identity": 0.5868207216262817, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/515300b9a58311806b3135800f4543b122845fcbba2d980ea22a178fba367ce1.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "52324c3886f74932f2faa17baa27d8264d03fe4db3d3096fd71687c3c962614c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1a0e30cd21bf08aa70b56b8973aa2e706f983362b8199e6eb769795660359374", "generation_seconds_batch": 23.60728953103535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.09409761428833, "genuineness": 4.3127899169921875, "identity": 0.7365045547485352, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/52324c3886f74932f2faa17baa27d8264d03fe4db3d3096fd71687c3c962614c.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "524511c0cef700e8a9b4e1f9631128f5d163d86f64d372c93c14be71b873fc6e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e9791cbd646932221f2635de82ba474a870ddc635d80e89146a43b71905f15a6", "generation_seconds_batch": 25.473619619035162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038779065012931824, "target_z": -0.39453125757368196, "ce": 6.300607204437256, "genuineness": 4.7081804275512695, "identity": 0.6686890125274658, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/524511c0cef700e8a9b4e1f9631128f5d163d86f64d372c93c14be71b873fc6e.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "52a2344222c4425b0c67a3f5e599b7a569ed527b7c5445b78d369d177431a4b9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4e89524ce735b84dce8ccf9e6a5ffa21f9bf43814a97bf5403481b687c63d874", "generation_seconds_batch": 28.602911591995507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.704906940460205, "genuineness": 4.6705241203308105, "identity": 0.6800461411476135, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/52a2344222c4425b0c67a3f5e599b7a569ed527b7c5445b78d369d177431a4b9.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "52bae095f3eb46222662aec20a5cd27615896460a2d2fcec28ec1a1b91fa1dac", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bded5b0345886360c9887019f3daa3e1abc1ed048f71b8cf2e673b48016d86af", "generation_seconds_batch": 25.04970232094638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.149696350097656, "genuineness": 4.406930446624756, "identity": 0.4918118119239807, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/52bae095f3eb46222662aec20a5cd27615896460a2d2fcec28ec1a1b91fa1dac.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "52bfe78e8fd48748192cc66d94ebd4252dc09dd79559dd188312b16514c4e3b1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1be842f61e40efd9c79c875ad3441105cb5a6ef875a40a7d7b0955c4e97dfa37", "generation_seconds_batch": 23.767313027987257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 5.879645347595215, "genuineness": 4.871357440948486, "identity": 0.7420600056648254, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/52bfe78e8fd48748192cc66d94ebd4252dc09dd79559dd188312b16514c4e3b1.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": "52c64041f207e7233c81443c47ce434f2164ebaafacfd80a5f64c9dac22c8187", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0aeb3f519ad8dcda57fed0ffbad230f06451d8a94f568db4183fbd04551e2be", "generation_seconds_batch": 26.851088853087276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.23706579208374, "genuineness": 4.758388519287109, "identity": 0.5056908130645752, "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_Jealousy_and_Envy/52c64041f207e7233c81443c47ce434f2164ebaafacfd80a5f64c9dac22c8187.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "52d74da09d022044c8f200eb681ab9c405d0eddededc6ec889c0914db8f4b80b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e6fba861acaedeee59fd3907b995968e7cfac9a4a7f6b8332bfb09e95cf50df7", "generation_seconds_batch": 26.574682892067358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.022613525390625, "genuineness": 4.381826400756836, "identity": 0.6388246417045593, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/52d74da09d022044c8f200eb681ab9c405d0eddededc6ec889c0914db8f4b80b.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "52f402481eeaa363f668aeb794dbc751a4542332ff66991eda28f59fc20ebf21", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8e71bbd0331f0d008b15887b58cc998aaaf86d9caf26fab441e6d4a1375962fe", "generation_seconds_batch": 26.893575283000246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.744620323181152, "genuineness": 4.557555198669434, "identity": 0.6581680774688721, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/52f402481eeaa363f668aeb794dbc751a4542332ff66991eda28f59fc20ebf21.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "5329f2bbb7006c335e9dcf9fa38a28ebf342277ea19391060b560ea6f5d4b389", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3ea8d316ac0967fbc18e7c64358c85dc7303e235df697d05538e1b74cb346645", "generation_seconds_batch": 25.605951708974317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.1894097328186035, "genuineness": 4.645420074462891, "identity": 0.7631223797798157, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5329f2bbb7006c335e9dcf9fa38a28ebf342277ea19391060b560ea6f5d4b389.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "541116334fe0e297297012d57b54130478361c6f84a5e463532f5034c742e57a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3fdad2a8d4f4b94851b69d507e3656642656355bfbaa199917b7ad3cee057024", "generation_seconds_batch": 24.91255910496693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.95112943649292, "genuineness": 4.15588903427124, "identity": 0.3422160744667053, "hypothesis": "The 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_Jealousy_and_Envy/541116334fe0e297297012d57b54130478361c6f84a5e463532f5034c742e57a.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "5424df51e4ef78245c51af0200ee88975bde55f4a6a478aa643541f2327b3d0b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "caba2f22774548e40f8e04fa5d48daa04cd707e4809af003a9c705ff319eca21", "generation_seconds_batch": 18.697453832020983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.998785495758057, "genuineness": 4.406930446624756, "identity": 0.6838661432266235, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5424df51e4ef78245c51af0200ee88975bde55f4a6a478aa643541f2327b3d0b.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "5427f3cbc0aa5a4c69eb34d5a92de73390cc74e29df7cacbb22c27cf4c83be72", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d9bfffb78618418702fde1fb7d7203c0ccfc036d391b01b4508a2321d1e1efa7", "generation_seconds_batch": 27.585448164027184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 5.244231700897217, "genuineness": 4.381826400756836, "identity": 0.5814932584762573, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5427f3cbc0aa5a4c69eb34d5a92de73390cc74e29df7cacbb22c27cf4c83be72.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "8eed535df37518bfc1a8e3113a6d46f73183883b03378db9cec8495019be7f2a", "generation_seconds_batch": 17.845083377091214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.340320587158203, "genuineness": 4.149612903594971, "identity": 0.4983852505683899, "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_Jealousy_and_Envy/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "549736bfe8fbf86a3d077c69d96a6e674865b17a93ec9a1f590699e4f13b0785", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "25d04244756d72a94b4d1ad9214432d5a51716b0585f1729a0a6ad4319956778", "generation_seconds_batch": 25.372179500060156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025719687342643738, "target_z": -0.4238281397556217, "ce": 5.736677646636963, "genuineness": 4.7458367347717285, "identity": 0.7176161408424377, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/549736bfe8fbf86a3d077c69d96a6e674865b17a93ec9a1f590699e4f13b0785.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "54bb4c84fe338f8cc2369b98439559ddd0aab02324f51149ea54a81cb99d00b6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "11b8b0f3384de3bae08c26b11d447f7e3f8af1c9d62696bb595961d9e6424e6e", "generation_seconds_batch": 25.222252093954012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.109982967376709, "genuineness": 4.482243061065674, "identity": 0.6642504334449768, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/54bb4c84fe338f8cc2369b98439559ddd0aab02324f51149ea54a81cb99d00b6.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": "55eb29cd960f9aa0bbfed24bf5f40e45ab8735909ab12e87c36a11b16aaab45a", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The keys are on the kitchen table.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc238a565e71960742fda96163ccb6e6169bc356ae72a3744544473426424382", "generation_seconds_batch": 24.68429503403604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.252951145172119, "genuineness": 4.381826400756836, "identity": 0.07550250738859177, "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_Jealousy_and_Envy/55eb29cd960f9aa0bbfed24bf5f40e45ab8735909ab12e87c36a11b16aaab45a.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "56509fbddbe811c95925b77e48e5d256b89bad8a3b7ca58c5eff9f1116caf1c1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e64aec00eb173974ccad80de515f5c5a22cdece6c58a3bdfd6c471f116d599ff", "generation_seconds_batch": 23.53988604794722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.062326908111572, "genuineness": 4.7458367347717285, "identity": 0.7960686683654785, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/56509fbddbe811c95925b77e48e5d256b89bad8a3b7ca58c5eff9f1116caf1c1.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "567a421ec94e19b07318498ce014187ced412b722200366a40c11b4de5171227", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4bf5503b14df98a8eb4028fe7de4d92adbe25ed3c5b2d09c21fd766a4933becf", "generation_seconds_batch": 24.77463306696154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.967014789581299, "genuineness": 4.381826400756836, "identity": 0.6386793851852417, "hypothesis": "De deur 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_Jealousy_and_Envy/567a421ec94e19b07318498ce014187ced412b722200366a40c11b4de5171227.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "5682c2948fe877f7d0b30176995007172760df80b137885b1132acf64e8610ae", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9a49389c837514f75dddafb495942f587fa7966b9892b8fd86e5aa96a7c2cd20", "generation_seconds_batch": 23.12684530497063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 6.038498878479004, "genuineness": 4.124508857727051, "identity": 0.6622482538223267, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5682c2948fe877f7d0b30176995007172760df80b137885b1132acf64e8610ae.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": "56e3d770ee46d135c272ae074bb675ffac90c3186c73f4c9d5696067777b44fe", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "8e219a1d4fedab7c9ea378c89213ccdb031b06f0813930d8f9b0bfa4c215580f", "generation_seconds_batch": 19.23445519199595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 6.006728172302246, "genuineness": 4.557555198669434, "identity": 0.6403810977935791, "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_Jealousy_and_Envy/56e3d770ee46d135c272ae074bb675ffac90c3186c73f4c9d5696067777b44fe.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": "57b615265c75c2e6814aa2b203917858dc9e78c40a1339fe979a53411184583b", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Your message arrived after I had left.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "25cb4a68b661b9485b72d6a9234a2a796ca307ddf42c822acfbd916ae243c7f8", "generation_seconds_batch": 18.34335177799221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.356205940246582, "genuineness": 4.419482707977295, "identity": 0.3109418749809265, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know and we can talk.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/57b615265c75c2e6814aa2b203917858dc9e78c40a1339fe979a53411184583b.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "583e152e540afcea05cf963acd8df07a90404714ca0d48568fcf34f7309f7cba", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d6b2b8c61cfbab0365562672c565b136bdead6bba65c4c48248fd709c1b4a617", "generation_seconds_batch": 17.110921034007333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.332377910614014, "genuineness": 4.494794845581055, "identity": 0.20668646693229675, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/583e152e540afcea05cf963acd8df07a90404714ca0d48568fcf34f7309f7cba.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "58ec647751a18023548316c8026d845bc6b740d1704bc87aa47da3954c3ba8af", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c573cc75d762687647a7de2334e3e94da7377aff47684c68eb4f4e93a7482fe1", "generation_seconds_batch": 24.93342735094484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 5.8875885009765625, "genuineness": 4.268857479095459, "identity": 0.40800076723098755, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/58ec647751a18023548316c8026d845bc6b740d1704bc87aa47da3954c3ba8af.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "599d109cc105edcd36a78f6249e0c2316f4d3b6020e3eb10a979031d08c1103c", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4a9eebf508ca1ecbd6eab7e6780a761a43f80a138ab9153d99ac2187121023c9", "generation_seconds_batch": 19.29978649294935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.7270262837409973, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/599d109cc105edcd36a78f6249e0c2316f4d3b6020e3eb10a979031d08c1103c.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "5a5b8d45e81cbad94af4cf5960332c9152d2cf575ae9403fd33ed22f8ff4166e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c7ec014988ca44056b40d63bb1becc79c7b41f53ca456afac3d7c1cd90f4aa03", "generation_seconds_batch": 26.335930843022652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.2767791748046875, "genuineness": 4.193545341491699, "identity": 0.8069677352905273, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "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_Jealousy_and_Envy/5a5b8d45e81cbad94af4cf5960332c9152d2cf575ae9403fd33ed22f8ff4166e.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "5a7cffc52b134de5a8ff3620abec3efdf93da00be6bdd3dfa6637cbfe8c912d9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fa73b4ce4ee1712cdbf5f01e8449b3eb49d362d7f86f41a744037adfc1af3370", "generation_seconds_batch": 24.78775116696488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.086154937744141, "genuineness": 4.570107460021973, "identity": 0.7839101552963257, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5a7cffc52b134de5a8ff3620abec3efdf93da00be6bdd3dfa6637cbfe8c912d9.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": "5a93c1546d90eee3f1cc9b7b5ef446922560d77027f3e45466a433a6e74fca1d", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "54574ecd66ccaae5f5e113614924a4839dedbfb77bb414abc45d5a431c0e55df", "generation_seconds_batch": 25.840192414005287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 5.569881439208984, "genuineness": 4.545003414154053, "identity": 0.819833517074585, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et verifie les two derniers chiffres. Appelle-moi quand tu aurais moment.", "wer": 0.18181818181818182, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5a93c1546d90eee3f1cc9b7b5ef446922560d77027f3e45466a433a6e74fca1d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "5a9a1af27f3451f892ef5a0477f69e431ea3a326e4a30c1be411255c02c3e95d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6448123a55447235ce4335bc1b27f0d03f969bfc1005b9fe0af0daf2978d5cb1", "generation_seconds_batch": 27.879633246921003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 5.804190158843994, "genuineness": 4.494794845581055, "identity": 0.4870961904525757, "hypothesis": "De deur 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_Jealousy_and_Envy/5a9a1af27f3451f892ef5a0477f69e431ea3a326e4a30c1be411255c02c3e95d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "5b89827a60a12020d680d2f1e06790ac74a7bc8e6e2e5c6131ea540b6db9f1d3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "70117ddc82d0bf20df7d968940be74d42b318e05f92a7a402bdb9228ccb7784d", "generation_seconds_batch": 19.06382830394432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.7078256607055664, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5b89827a60a12020d680d2f1e06790ac74a7bc8e6e2e5c6131ea540b6db9f1d3.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "5c04533e4b59549850c6d247da21dd0f79f518328a4254fc1add2a04ee6e1cee", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "789728fb7ab19e869a75767a5d36a53d6a5943854f89843eb7e675a6ee960964", "generation_seconds_batch": 22.870848860940896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.332377910614014, "genuineness": 4.444586753845215, "identity": 0.6016818284988403, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5c04533e4b59549850c6d247da21dd0f79f518328a4254fc1add2a04ee6e1cee.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "5c2a758d1d16e9d9e27d75edb433e1dcb6462bfad3183232f56238871119010e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d05d320fe711bf9ed3a04a0f289c56b7507fc2d53fb0697ff3cf0af5eef56c11", "generation_seconds_batch": 23.873111734050326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.998785495758057, "genuineness": 4.256305694580078, "identity": 0.7440789341926575, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5c2a758d1d16e9d9e27d75edb433e1dcb6462bfad3183232f56238871119010e.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "5c8406b6fe9a3d88da760979c3da99ce9c400e1ca91df23f53fbb16d63387f9e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "65e426b6833e5faf9a3205bd341b12f33c64f7f9bf82f001638ae73443b1b1d6", "generation_seconds_batch": 26.185181564069353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025719687342643738, "target_z": -0.4238281397556217, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.4443603456020355, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5c8406b6fe9a3d88da760979c3da99ce9c400e1ca91df23f53fbb16d63387f9e.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "5cb39085805c2bfdc82bf5c9be30c0d33530d7481cf89da8daea9d0844ecb88b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0503b2ee76d8e65e889dccc82a0369d867132cb9e5a6e06efcc9fdd22eb11db4", "generation_seconds_batch": 24.80721532809548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.557967185974121, "genuineness": 4.3504462242126465, "identity": 0.42768624424934387, "hypothesis": "De deur 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_Jealousy_and_Envy/5cb39085805c2bfdc82bf5c9be30c0d33530d7481cf89da8daea9d0844ecb88b.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "5cd5dec508623d5083261d0916131a15cefa8ea0ac8cf4ec08ea812471d9dff0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b77cbaa2f6f587a6104322be9d05c45537c12c9b4f45899b6159ff4fc73ff5eb", "generation_seconds_batch": 25.23997708701063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.764476776123047, "genuineness": 4.595211505889893, "identity": 0.6587163805961609, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5cd5dec508623d5083261d0916131a15cefa8ea0ac8cf4ec08ea812471d9dff0.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "5cf27845efc57be9982ca293753336c7eff02382c3535c80ac805e04a5d8f3d2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d86ce240cb77a8bd0a7269f1cecb7a0c37df0a49e0489b23390cd17099a2e4ef", "generation_seconds_batch": 25.522637429996394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 5.696964263916016, "genuineness": 4.425758361816406, "identity": 0.6707802414894104, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5cf27845efc57be9982ca293753336c7eff02382c3535c80ac805e04a5d8f3d2.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": "5d3cac7679505b762ed63ed32f58ff907bad0fa78760409ec140fd4ed060aa7c", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33855040354996cc8af33271337c6c2ce4c2d654806af932ffb502a0303521a0", "generation_seconds_batch": 25.261432219063863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.078212261199951, "genuineness": 4.532451152801514, "identity": 0.6776764392852783, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lun 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_Jealousy_and_Envy/5d3cac7679505b762ed63ed32f58ff907bad0fa78760409ec140fd4ed060aa7c.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "5d54d7abcf50cd7c329306035231f39fc885cdd9628238ab80b4f416807641a7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dceca60e6ccef5155980a085b9707f61a99e5c573386faac650f681f872cae49", "generation_seconds_batch": 18.53689101000782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.022613525390625, "genuineness": 4.306513786315918, "identity": 0.6571348905563354, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "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_Jealousy_and_Envy/5d54d7abcf50cd7c329306035231f39fc885cdd9628238ab80b4f416807641a7.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "5d797dc1864ee18b7c23fee5ca785596dade89bb4831e45e75bcbe0cdced672f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f05b01231c75642b9662f05e70ecda5ca32cde340320a39f4d0890b136090000", "generation_seconds_batch": 19.512237248010933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 5.847874641418457, "genuineness": 4.432034492492676, "identity": 0.7747393250465393, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5d797dc1864ee18b7c23fee5ca785596dade89bb4831e45e75bcbe0cdced672f.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "5d9f84aa3541d7a3d554f42b6e965c25ce7a7ee3e7745ad5134e4ce7dc5fe2ee", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e7a9d3189e5cf96d9358158378fbe6a669bf421cd2f22d8c467b570cc7adbf21", "generation_seconds_batch": 23.767313027987257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.982900142669678, "genuineness": 4.808597087860107, "identity": 0.7223412990570068, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5d9f84aa3541d7a3d554f42b6e965c25ce7a7ee3e7745ad5134e4ce7dc5fe2ee.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "5db770dfe21b493929fdc98ff11ce727f0e7a21683116e5a1b9eb7b4ab5d11e9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9301fdc3383d96b4696a8c6c72214029e5609d8bbe052c148cc919f26307f801", "generation_seconds_batch": 25.23432087607216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.7684478759765625, "genuineness": 4.519899368286133, "identity": 0.7813421487808228, "hypothesis": "J'ai trouvé la petite boite. Elle était près de la vieille fenêtre. We pouvons regarder ensemble ce qu'elle contact.", "wer": 0.15789473684210525, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5db770dfe21b493929fdc98ff11ce727f0e7a21683116e5a1b9eb7b4ab5d11e9.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "ad028ae402456003efe7af779233c7ffabe6642946402c28bc806ee480bd2684", "generation_seconds_batch": 16.44386429199949, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 5.990842819213867, "genuineness": 4.218649387359619, "identity": 0.8096816539764404, "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_Jealousy_and_Envy/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "5eab4374453393db752cf670fbe86b72358b437ec72d746a9049acaf097dcc9a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a45bcb3d4ec70459258f5308843de0ff23e6526d3c9be15dfc3be5c7773144fe", "generation_seconds_batch": 28.051124901976436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.419747352600098, "genuineness": 4.394378662109375, "identity": 0.275847852230072, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5eab4374453393db752cf670fbe86b72358b437ec72d746a9049acaf097dcc9a.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "5f47d1d22b05195e705157e545f1fdd4c3a3d0cf9e9fa41aba486339fef69b05", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fc8fb450ade51bd85de048f19468c3696ba2a944baeb8160ccfab18e9dbc77ed", "generation_seconds_batch": 27.879633246921003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.871703147888184, "genuineness": 4.494794845581055, "identity": 0.561092734336853, "hypothesis": "De deur 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_Jealousy_and_Envy/5f47d1d22b05195e705157e545f1fdd4c3a3d0cf9e9fa41aba486339fef69b05.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "5f90ce86a53451187d192931f8a74a1f1b7f69021ecbe97daaba9e43501defbb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "753aaecf2010cffc5cade4addf045e07542ae4dcd3fd22fd0b5b5ead9ee21a39", "generation_seconds_batch": 26.56543734599836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030943438410758972, "target_z": -0.4121093868828458, "ce": 5.728734970092773, "genuineness": 4.507347106933594, "identity": 0.6896668672561646, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5f90ce86a53451187d192931f8a74a1f1b7f69021ecbe97daaba9e43501defbb.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "5f9dabb9881a4682b7857d9043e0a5e022c9765ca8ef22331b82307ca5d73694", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "09cbdbfa838cf7364c7e00d8eab753fd58095a854912a095bd0aa1d795dfb9fb", "generation_seconds_batch": 19.5866262819618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.974957466125488, "genuineness": 4.369274139404297, "identity": 0.5859706401824951, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5f9dabb9881a4682b7857d9043e0a5e022c9765ca8ef22331b82307ca5d73694.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "5ff249941d480a70df8d08d5741465d8f6fd617466bf3e2e6525e6070e89d0de", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c17d08cd5deb09af80c7bc747e123b4685c13cca59a60d7b7cf04bee0b114815", "generation_seconds_batch": 28.89545063301921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015199676156044006, "target_z": -0.5156249926874795, "ce": 6.38003396987915, "genuineness": 4.469690799713135, "identity": 0.252201646566391, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5ff249941d480a70df8d08d5741465d8f6fd617466bf3e2e6525e6070e89d0de.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "5ffbcb89af2b105ea7472ccefbd36ba7f8396d8def9614ea3a02c9e79a854f13", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b957a82aa8bec9a0781adc2938e0fca973d6e4633a1879a858912e70a4557d67", "generation_seconds_batch": 24.99286378803663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.38003396987915, "genuineness": 4.570107460021973, "identity": 0.26848945021629333, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/5ffbcb89af2b105ea7472ccefbd36ba7f8396d8def9614ea3a02c9e79a854f13.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "6036b529ef5c0d1808e7d10ab755528c35d90dbc3f21e57ed447350bc4ae53f2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f56189bd13a217e4756767a183e36e639f960501df764c5eaa1977510b8e8973", "generation_seconds_batch": 25.231162413023412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.95112943649292, "genuineness": 4.7332844734191895, "identity": 0.6669785976409912, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6036b529ef5c0d1808e7d10ab755528c35d90dbc3f21e57ed447350bc4ae53f2.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "610f5ce0d22470e5d229e0db76f487f6f230cade5155edbb7b5ec15ebfa4de1d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "51baac88490f4fef5d2ede4cdf611b92728183398dd430da7c2200ee86abf603", "generation_seconds_batch": 24.9541382570751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 5.629451274871826, "genuineness": 4.268857479095459, "identity": 0.7317671179771423, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/610f5ce0d22470e5d229e0db76f487f6f230cade5155edbb7b5ec15ebfa4de1d.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "6116f28446016fb2863776d7ab05bfebc0d74e1e08475cb74c860073c63f7bbd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0facdc08f4b1f103fb1400ce1369498ee530c8e71776a1d71061b3cf85a4adc", "generation_seconds_batch": 19.301650766981766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.260893821716309, "genuineness": 4.15588903427124, "identity": 0.2027994990348816, "hypothesis": "The 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_Jealousy_and_Envy/6116f28446016fb2863776d7ab05bfebc0d74e1e08475cb74c860073c63f7bbd.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "6118524172c55632588825aad1b126ae325ef0d81fa061231397e75412dcfff8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "63911fbdc4a64e02aa1e425982d3661a17eec8265da9d872083d0acdeb1ccad1", "generation_seconds_batch": 25.765472241095267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.023905932903289795, "target_z": -0.5351562586183277, "ce": 6.054384231567383, "genuineness": 4.419482707977295, "identity": 0.8065727353096008, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6118524172c55632588825aad1b126ae325ef0d81fa061231397e75412dcfff8.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "6167e420ed1aae21e95e07be30e7ed990a60d5f24575adb4e56b014dd663067a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f90d012916bd65265e944255f5b9146a103b76f13c35c948cdaaae748cd01130", "generation_seconds_batch": 25.829414322040975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 6.0305562019348145, "genuineness": 4.243753433227539, "identity": 0.2765716314315796, "hypothesis": "The 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_Jealousy_and_Envy/6167e420ed1aae21e95e07be30e7ed990a60d5f24575adb4e56b014dd663067a.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "61685a18d6b65224f219d3f24cc507a76200b3e8870b2c9a8bf07c4f86c64cc1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "09aa46910b5536332bf151a5f6c7c0bf8a58e5b93ff778a2bf7bace9bdaef3ea", "generation_seconds_batch": 18.16060613305308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.0146708488464355, "genuineness": 4.356721878051758, "identity": 0.1403568685054779, "hypothesis": "De deur 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_Jealousy_and_Envy/61685a18d6b65224f219d3f24cc507a76200b3e8870b2c9a8bf07c4f86c64cc1.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "6172b86cb83907636cb16e3168cf11dd478a1e7ace17c36144a0b2ca826a46a8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "21963ce4f17175ded195b71db71542e97059597abe15eab38e11626a1580c434", "generation_seconds_batch": 25.25249009404797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.205295085906982, "genuineness": 4.369274139404297, "identity": 0.07720598578453064, "hypothesis": "The 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_Jealousy_and_Envy/6172b86cb83907636cb16e3168cf11dd478a1e7ace17c36144a0b2ca826a46a8.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "61779e1f8f393a077a6ff7f1ca9353c4d007e14a0f78498fcca2b2b073906033", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cde2a6dd7c60ea610830cb46a4a6afc1d17cca2ea8b9b46ea820b451591a4717", "generation_seconds_batch": 25.164790660026483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.117925643920898, "genuineness": 4.607763767242432, "identity": 0.7044530510902405, "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_Jealousy_and_Envy/61779e1f8f393a077a6ff7f1ca9353c4d007e14a0f78498fcca2b2b073906033.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "61b34a86389f5d88014367a08b981b57dd7144b881c1a048fb57648cb4b03518", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3398d2aa7ac623624fe0713fe2224a9a43493f2e7fda086eaf6b9f49bfe01a14", "generation_seconds_batch": 18.3498158500297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.268836498260498, "genuineness": 4.15588903427124, "identity": 0.2489386647939682, "hypothesis": "The 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_Jealousy_and_Envy/61b34a86389f5d88014367a08b981b57dd7144b881c1a048fb57648cb4b03518.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "6223fdd37e3acac137920bd1a59fffa515a848a689c41836ecb8ee1506743382", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4d3d4482a9f592013f9e71abe5d1d1ea00fb679b29f5abbb7508c4a12ccfab65", "generation_seconds_batch": 25.23997708701063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 6.213237762451172, "genuineness": 4.65797233581543, "identity": 0.5618891716003418, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6223fdd37e3acac137920bd1a59fffa515a848a689c41836ecb8ee1506743382.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": "6235e19b04861a87f49983b0e5b9c0fac8e65bc78d0418cce1677cda8c7a5391", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The road turns left behind the bridge.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "756a8dfa2c06d9213626b5dd5e282ec06fdf8ae3112add73fe1933b7d8b556a0", "generation_seconds_batch": 25.25815057696309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.23706579208374, "genuineness": 4.243753433227539, "identity": 0.4757845997810364, "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_Jealousy_and_Envy/6235e19b04861a87f49983b0e5b9c0fac8e65bc78d0418cce1677cda8c7a5391.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "629ac140156fd82d94808a8719af4c45e6370c3c03db0b679969292618f55a96", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "28740cdff543344c83ee1525b2ee3e20c1dfd81b37340357782f74ecef5694fa", "generation_seconds_batch": 25.59619923797436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.213237762451172, "genuineness": 4.808597087860107, "identity": 0.6671972870826721, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/629ac140156fd82d94808a8719af4c45e6370c3c03db0b679969292618f55a96.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "62eec58c94ae761319c1373ede50a61d905aac8a208456fc4fefa409ad1ac27c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "663747708ab0d90f2f63b2cb34672d8882fcd88bed8cb41b6fb447e58e9a5a87", "generation_seconds_batch": 24.30811750900466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.831989288330078, "genuineness": 4.482243061065674, "identity": 0.5744162201881409, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/62eec58c94ae761319c1373ede50a61d905aac8a208456fc4fefa409ad1ac27c.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": "6302e411ec74a4135decc0cd7dd341c28bfea1cb1e6ca184dfa31ce1d7e65cbd", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7c78c0eeea20d6bff4e615fdae8640d050bcac3f7847b1bd8405e2a6f3d928cf", "generation_seconds_batch": 20.77451357198879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 6.0146708488464355, "genuineness": 4.7834930419921875, "identity": 0.6970330476760864, "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_Jealousy_and_Envy/6302e411ec74a4135decc0cd7dd341c28bfea1cb1e6ca184dfa31ce1d7e65cbd.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "6357bd9006adddebf66583bebc5ebf39ffbdd6da9bd37b737058b08e0dd0e1d2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a5f0978c60d533b1702d392ad4a47b5e418db74a198b27cd724c6aa770139248", "generation_seconds_batch": 28.800194176961668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 5.847874641418457, "genuineness": 4.871357440948486, "identity": 0.8293318748474121, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6357bd9006adddebf66583bebc5ebf39ffbdd6da9bd37b737058b08e0dd0e1d2.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "63f5da7df606c0ac3b821bf5b8c93bd5bdadb10d1cb5a7819baab7b790be669a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0bef482758e07c28b583622b9b18ddbd586551390757ee0d671a863802c98e37", "generation_seconds_batch": 26.024463378009386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 5.577824115753174, "genuineness": 4.6956281661987305, "identity": 0.7890421152114868, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/63f5da7df606c0ac3b821bf5b8c93bd5bdadb10d1cb5a7819baab7b790be669a.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "647c829e3c134154dc832239def4aeca3edf9e566917d1dc42115d9226a91056", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "35dcb81757a838b4edcfa30f96e4be214039d399b26471f43774bd7b65c7e521", "generation_seconds_batch": 18.530879847938195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.41180419921875, "genuineness": 4.093128204345703, "identity": 0.6741746664047241, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/647c829e3c134154dc832239def4aeca3edf9e566917d1dc42115d9226a91056.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "64cfecd7106316c49bbd6a5f5a726fb7cb75dae2c996a807d5ca385790edd50d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e54ed8e0869531e1aff26932eb8cdd6f8c881fdfb2044a53139f52101f03b792", "generation_seconds_batch": 25.21281693293713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.240260601043701, "genuineness": 4.482243061065674, "identity": 0.7782651782035828, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/64cfecd7106316c49bbd6a5f5a726fb7cb75dae2c996a807d5ca385790edd50d.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": "653d07a8c23a199fbc331eda917ef63f325f288fc93b7d03cff7df063967905e", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba7e558315f87be27e8cc33e7ccebe0ba4c39c99e640c2cd3d3bcb1b86115439", "generation_seconds_batch": 26.10714450397063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.935244083404541, "genuineness": 4.532451152801514, "identity": 0.6010214686393738, "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_Jealousy_and_Envy/653d07a8c23a199fbc331eda917ef63f325f288fc93b7d03cff7df063967905e.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "655e744411d2e80ed97f15e4cfc8dc1c26cfa4e66e6013527d84ee4b161e7faa", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3b1f5ddd6b8d24f1c0c1d4be6602d9ebcadc7a46ea0deb7d626dbfe22dc6a46a", "generation_seconds_batch": 26.74932188994717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 6.149696350097656, "genuineness": 4.287685871124268, "identity": 0.7056282758712769, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/655e744411d2e80ed97f15e4cfc8dc1c26cfa4e66e6013527d84ee4b161e7faa.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "6585cae2400e93eebd4885825df3177b51e0841688c3391933d46fb6972a17ba", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d1043c23f6b8b6297af8c833ec22f8a01b46aca4eca7b03cdeb0f3e20bddd56c", "generation_seconds_batch": 18.605538545991294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027460947632789612, "target_z": -0.419921866512253, "ce": 6.173524379730225, "genuineness": 4.7834930419921875, "identity": 0.7331638932228088, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6585cae2400e93eebd4885825df3177b51e0841688c3391933d46fb6972a17ba.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "659ac0d546b41c2a069f480318f3854c71b42e750b334c34337b4a9717ba7d09", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7212d726461f644de89e7db5495e790cb1b0f37059e5f815e324187a95fdc0b3", "generation_seconds_batch": 25.8323218600126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.0146708488464355, "genuineness": 4.362998008728027, "identity": 0.3792659640312195, "hypothesis": "De deur 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_Jealousy_and_Envy/659ac0d546b41c2a069f480318f3854c71b42e750b334c34337b4a9717ba7d09.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "66562e8c21117d643ef0db78b8209e6000fffc154ceb1908ef6475df40c0f935", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "35c1157fb56447e628bac2d81f80af4d4842481392f852689103fdc553f6fb3c", "generation_seconds_batch": 25.110205846023746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.443574905395508, "genuineness": 4.2374773025512695, "identity": 0.5183592438697815, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/66562e8c21117d643ef0db78b8209e6000fffc154ceb1908ef6475df40c0f935.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "66730859894737244dc736ccf608e4702e53dbe91d2796413a119fa13ab107f0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e65c5ef58fa8689773580b9d2580db5e3138d1716145ab209ca4b0c90c01121", "generation_seconds_batch": 18.62888325599488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.40031149983406067, "hypothesis": "The 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_Jealousy_and_Envy/66730859894737244dc736ccf608e4702e53dbe91d2796413a119fa13ab107f0.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "668dcbeba8456094a0994863f731d68767d353eed881e100cb763d77f4ce7cfc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2623f938299481d9eea604993d6ca249cdf0cd717bb9c42809a1786ada495a90", "generation_seconds_batch": 19.611683181021363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 5.784333229064941, "genuineness": 4.758388519287109, "identity": 0.8454698920249939, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/668dcbeba8456094a0994863f731d68767d353eed881e100cb763d77f4ce7cfc.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": "66d4c20d3a7ab6b375f93f88972690ec4f0172220ec2df90232a007f30a4b2d2", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I wrote the number on the envelope.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97c3a666ac151c729a28da365d9bccd80290e7b5b890b4ee7d936d40bf232ef3", "generation_seconds_batch": 25.67459701898042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.260893821716309, "genuineness": 4.13078498840332, "identity": 0.2556292712688446, "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_Jealousy_and_Envy/66d4c20d3a7ab6b375f93f88972690ec4f0172220ec2df90232a007f30a4b2d2.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "686e2d2114079134d70be5e9fa1a40ebeb6a39b0973ec5761cc0df83d6782750", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "43a839863cc5d3f3508ba9a071463d0ebcde764caa599acc76ed18d8ca4bce7b", "generation_seconds_batch": 25.400460949982516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029202193021774292, "target_z": -0.4160156266975494, "ce": 6.09409761428833, "genuineness": 4.632867813110352, "identity": 0.8160425424575806, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/686e2d2114079134d70be5e9fa1a40ebeb6a39b0973ec5761cc0df83d6782750.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "687e795928889bcc149e7dee9685ff87b10b8f2b5f9746d1b252ed62364484c0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "23d66a98275302eb2a9b1e5c606a17d247bdcfffc0c7a9423ea2be44221acce2", "generation_seconds_batch": 25.779991761082783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.086154937744141, "genuineness": 4.507347106933594, "identity": 0.6244702935218811, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/687e795928889bcc149e7dee9685ff87b10b8f2b5f9746d1b252ed62364484c0.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": "6996fefdb594c83b49094b58cc4cdfe65154de85ce13403ac4886f70be9f31ca", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "227304cff4a642440f2b098f8942b5d1439be8c11caa984628de20c0c2e6b70b", "generation_seconds_batch": 19.6787010099506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01868218183517456, "target_z": -0.5234375057455518, "ce": 5.593709468841553, "genuineness": 4.645420074462891, "identity": 0.8317999839782715, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lille bien et verifie les deux derniers chiffres. Appelle moi quand tu aurais.", "wer": 0.2727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6996fefdb594c83b49094b58cc4cdfe65154de85ce13403ac4886f70be9f31ca.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "69ab5d1d337532108d7986e29a71f5d2f9b70976aac0f11bf2ca8f2ecd0d609e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9900ad6a6c6f37a03dd467de2838a6e3c62f4289603ae579cd93861cdcf220cf", "generation_seconds_batch": 25.065250448067673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 5.371314525604248, "genuineness": 4.337893962860107, "identity": 0.7150562405586243, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/69ab5d1d337532108d7986e29a71f5d2f9b70976aac0f11bf2ca8f2ecd0d609e.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "69b840ca460ddbb2f64aeee9887f39db4a182c0f4e8b6ce192b1f4bef9a4cd6e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "240cf6d7c94eb35b73bb756910bccdaaaa02df9b70912bdd2e4290ad7965c496", "generation_seconds_batch": 24.744648523977958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.95112943649292, "genuineness": 4.7081804275512695, "identity": 0.5689645409584045, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/69b840ca460ddbb2f64aeee9887f39db4a182c0f4e8b6ce192b1f4bef9a4cd6e.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": "69cf43808d420c4094a9be7d76c8d17114db0d5fd3f6963c9a89b13fcfeef1cb", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The road turns left behind the bridge.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9f93bbf276dc2e3c238e376f2f4273825a92687fdcf656854d60272f5ec9b780", "generation_seconds_batch": 19.14994259609375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.213237762451172, "genuineness": 4.394378662109375, "identity": 0.26788362860679626, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/69cf43808d420c4094a9be7d76c8d17114db0d5fd3f6963c9a89b13fcfeef1cb.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "6a514f3ec62d16fbf9ad05694cafa9638735c1fcd5ddcf22a825187efdeed335", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb4262b1d8caa6ab310d7125a0dfc4c48f5896c54d36e01101bda70611d4f9fc", "generation_seconds_batch": 24.91255910496693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.086154937744141, "genuineness": 4.356721878051758, "identity": 0.22134695947170258, "hypothesis": "The 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_Jealousy_and_Envy/6a514f3ec62d16fbf9ad05694cafa9638735c1fcd5ddcf22a825187efdeed335.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00161f1bd2f36f2d304a1e4a3ff81e42043e4613d577513a895a6bd55ba3366c", "generation_seconds_batch": 19.281523138983175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 6.372091293334961, "genuineness": 4.118232727050781, "identity": 0.3009076714515686, "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_Jealousy_and_Envy/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "6a7e10e298f56e7336e62e28e6d5947b89272e6d4072f82e68ea1b1a5935a5b4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4fd267dfc7d37eb144355dc238018e3d95f73dec1fc1c2a0495608c402246c1f", "generation_seconds_batch": 24.30811750900466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.824047088623047, "genuineness": 4.507347106933594, "identity": 0.8000449538230896, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6a7e10e298f56e7336e62e28e6d5947b89272e6d4072f82e68ea1b1a5935a5b4.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "6abab84dc4bc4a67d07b69e9551758b12c2f52c85d5879b50c2a1eb6bfb246fb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c26d4086e23d950c796aeebf07a08770a303ad8006250cfa1577e71c7c1626c9", "generation_seconds_batch": 18.6099129000213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.284721851348877, "genuineness": 4.419482707977295, "identity": 0.5412054061889648, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6abab84dc4bc4a67d07b69e9551758b12c2f52c85d5879b50c2a1eb6bfb246fb.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": "6b2c3fc6be8370e048feb9ee0211f9282138e51c0ed3d00d56242f0503c9e5ee", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Someone moved the little blue chair.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "6e25f0654d40dea776def9240cf43b0566a65c9bf0f5eb6c7b2a8ed0977a085b", "generation_seconds_batch": 19.583416213048622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.260893821716309, "genuineness": 4.519899368286133, "identity": 0.2976069748401642, "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_Jealousy_and_Envy/6b2c3fc6be8370e048feb9ee0211f9282138e51c0ed3d00d56242f0503c9e5ee.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "44b6fcdc691d6c7f3b08f73fcca5af46bcc4c4e3f3f4efad220e227b5cde8c1e", "generation_seconds_batch": 18.67256733297836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.149696350097656, "genuineness": 4.494794845581055, "identity": 0.5540832281112671, "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_Jealousy_and_Envy/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "6bfe1e9a803a9d0956dffcd122a58473d23f42a6f83ca817c73e237270a3d914", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5ac9fccf9cbb453d36a0a75666dec3e4bf726bf830bcefe9f377ff00cae74d2e", "generation_seconds_batch": 25.484098410001025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.474569320678711, "genuineness": 4.457139015197754, "identity": 0.596259593963623, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6bfe1e9a803a9d0956dffcd122a58473d23f42a6f83ca817c73e237270a3d914.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "6c40ddf3d29aa305ea82f58066baa3d156c57e8c9e4f730975e5a0b893c84320", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8126bd3f64dbbf822ab0c82d30b9a047ffaea75636bfd6e58a2ef2c6048918c1", "generation_seconds_batch": 24.1181965979049, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.9431867599487305, "genuineness": 4.796044826507568, "identity": 0.7106531262397766, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6c40ddf3d29aa305ea82f58066baa3d156c57e8c9e4f730975e5a0b893c84320.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "6c6616c7c046e46f1de6be96e77f56e984aee282891990c737db4c6cbb25ace8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b49feb623582e49583e8bca9f28e9a31933c6f124441252bb89dcfc2bca3900c", "generation_seconds_batch": 24.271399033023044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.027388423681259155, "target_z": -0.5429687382477348, "ce": 5.919358730316162, "genuineness": 4.557555198669434, "identity": 0.8651257753372192, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6c6616c7c046e46f1de6be96e77f56e984aee282891990c737db4c6cbb25ace8.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "6c9d38e24b411823d19e8b67475ecfa2ec4c21e5a73a3ca47c3635bcdf36aeec", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3e60282bafcec59540310e5c71946c9557ad1ef89156c5bf0610611dc5796f6b", "generation_seconds_batch": 24.63604245998431, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.070269584655762, "genuineness": 4.319066047668457, "identity": 0.35910260677337646, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6c9d38e24b411823d19e8b67475ecfa2ec4c21e5a73a3ca47c3635bcdf36aeec.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "6cc9871e51c7f839c734115be7cf56465fa668ad4652574819ab8216f8317dd4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d802464bf422775f7e977ce8192773da022a3b259da74d9cfa0760e49f66cf7", "generation_seconds_batch": 19.74051514500752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 5.982900142669678, "genuineness": 4.432034492492676, "identity": 0.6894967555999756, "hypothesis": "De deur 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_Jealousy_and_Envy/6cc9871e51c7f839c734115be7cf56465fa668ad4652574819ab8216f8317dd4.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "6d091a2d888d76389d8b83b9095bbd593b88bc4cf994538bfae77f3985d32ad2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "11a0f53c0dd178249569488f051666ebf98a347e1520a111e7ffe8d9d186716d", "generation_seconds_batch": 31.937278143013828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 6.1894097328186035, "genuineness": 3.835810661315918, "identity": 0.24386703968048096, "hypothesis": "The 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_Jealousy_and_Envy/6d091a2d888d76389d8b83b9095bbd593b88bc4cf994538bfae77f3985d32ad2.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "6d947d1f77d69d5e6738642a8f7eed630af86032a892b1b93fba75edabebdf23", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a8fe99c9656d25cf3c2c82bea5af9926c82107fe6d91ff72da5cd22e9f0fca72", "generation_seconds_batch": 21.090732053969987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.078212261199951, "genuineness": 4.20609712600708, "identity": 0.7740785479545593, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6d947d1f77d69d5e6738642a8f7eed630af86032a892b1b93fba75edabebdf23.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": "6db008908a009d18307ce8501f8ea8f73781dc47d7f2240189f4634a4cf59d9b", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "95bf04b7c568d17e1321670bb5864c961187d6d9ff04323ae708a9d88daf4138", "generation_seconds_batch": 21.036978077958338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.086154937744141, "genuineness": 4.3881025314331055, "identity": 0.5552088022232056, "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_Jealousy_and_Envy/6db008908a009d18307ce8501f8ea8f73781dc47d7f2240189f4634a4cf59d9b.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "6dde6b4ea16198bd47b5d4bbfc3db9ca43a3488e6cce842427a0f6cb11c865a9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fda2178b405e9a039c7f6ffd9f43fb1955f9d49a7ded489ab87bc525c565d091", "generation_seconds_batch": 24.219958013971336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.022613525390625, "genuineness": 4.356721878051758, "identity": 0.75974041223526, "hypothesis": "De deur 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_Jealousy_and_Envy/6dde6b4ea16198bd47b5d4bbfc3db9ca43a3488e6cce842427a0f6cb11c865a9.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "6e41f3cae52150e9689a85612ae52b7a60f66f53dba955349125f03c1f293159", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a9c5b8935ee73f3b5c14a95480b3d8bedb7851b510f391fc05abfeeaec4c53fe", "generation_seconds_batch": 25.950248078093864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.8875885009765625, "genuineness": 4.645420074462891, "identity": 0.7881870865821838, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6e41f3cae52150e9689a85612ae52b7a60f66f53dba955349125f03c1f293159.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "6e4608377f919262d5b9f832f6ac1611740f7bc97a47632eddcddd059cefe347", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3a746ad1a5b794d562c161022e99e3568be2784accf4d64c116c4894124f8ffa", "generation_seconds_batch": 25.764146773028187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.6322913765907288, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6e4608377f919262d5b9f832f6ac1611740f7bc97a47632eddcddd059cefe347.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "6e7152339cb64c1b07b209e9a5aeb46065e255fcbffb2a13811fa03a3aa54f12", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6120b9184491517ad4a7673f2094021cf405872ba9de5a916141dcb085fd9ca6", "generation_seconds_batch": 27.52519336901605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 6.038498878479004, "genuineness": 4.6956281661987305, "identity": 0.6954270601272583, "hypothesis": "De deur 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_Jealousy_and_Envy/6e7152339cb64c1b07b209e9a5aeb46065e255fcbffb2a13811fa03a3aa54f12.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "6f03676f9bb31d14d468d4bc537dd621098c95a1911fe62336e67add6f0accea", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "130fbf068745d812615b41108e7c7ba3ace77ba914798eba8e1873965440e513", "generation_seconds_batch": 20.390295756049454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 6.09409761428833, "genuineness": 4.137060642242432, "identity": 0.6288350224494934, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6f03676f9bb31d14d468d4bc537dd621098c95a1911fe62336e67add6f0accea.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "6f631d6b90a694c90f653a3df9da1467ef1fd7c0c62c61e8fb335fcc4b1c0014", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 130, "seconds_generated": 10.4, "mp3_sha256": "15dd140326dc974fbcaa79e969e292a24345f6910161e69cc66dfddaa302f4c7", "generation_seconds_batch": 23.205528686055914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 5.319687366485596, "genuineness": 4.582659721374512, "identity": 0.6470401287078857, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos.", "wer": 0.23529411764705882, "duration_error_s": 0.20000000000000107, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6f631d6b90a694c90f653a3df9da1467ef1fd7c0c62c61e8fb335fcc4b1c0014.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "6fb4f5717f1c7783e85bc459c4469fb98f4e270700bdd46b10f454f8b98ddbb4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b575c356c847dd261bcdb7111bb2726d9b01618106a8318888b88c7416599fdf", "generation_seconds_batch": 24.58417611196637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 5.967014789581299, "genuineness": 4.482243061065674, "identity": 0.7318721413612366, "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_Jealousy_and_Envy/6fb4f5717f1c7783e85bc459c4469fb98f4e270700bdd46b10f454f8b98ddbb4.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "6fb5029efea1b529f4096206362556a1af65be1ccf86ff325329f65a23b831ba", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3d7277e340c7ca382b823f49202a77a7e8e4810a76e101d2940ccfcbd07dcdc8", "generation_seconds_batch": 25.370437199017033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029202193021774292, "target_z": -0.4160156266975494, "ce": 5.649308204650879, "genuineness": 4.6203155517578125, "identity": 0.6075310707092285, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/6fb5029efea1b529f4096206362556a1af65be1ccf86ff325329f65a23b831ba.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "70176ed9fe3353fdd23451e67e2084fec01f9ea0a3cb809beabe687059e0cc26", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9280828738b9f3d628a2f5b39fdfa5e9c636bbd3e0e284f0ec83c6f6031f5fb2", "generation_seconds_batch": 26.096314931986853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.205295085906982, "genuineness": 4.218649387359619, "identity": 0.41139093041419983, "hypothesis": "The 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_Jealousy_and_Envy/70176ed9fe3353fdd23451e67e2084fec01f9ea0a3cb809beabe687059e0cc26.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "7054e98255519833975f7399cc058db89938d29007e9ba1076983d3844e484e3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b2c9b85426d37730c0c47ea4fc2063af4e92048bb91864c007b9125740f3b8fd", "generation_seconds_batch": 19.06382830394432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.109982967376709, "genuineness": 4.394378662109375, "identity": 0.5893063545227051, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7054e98255519833975f7399cc058db89938d29007e9ba1076983d3844e484e3.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "7095f721c09f15c42217060e05cf1d556463b7951c94ab9e5a436a26a87a7ec0", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "652427e2de8ac38a90220995dde9c7a4e0d8668a22da4ce0fc4e8ba601159409", "generation_seconds_batch": 19.342694528982975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.23706579208374, "genuineness": 4.143336772918701, "identity": 0.2811271548271179, "hypothesis": "The 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_Jealousy_and_Envy/7095f721c09f15c42217060e05cf1d556463b7951c94ab9e5a436a26a87a7ec0.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": "70d66de0f6abc9c3ef9873433aeefd45fca07878807abacb348f0ec598aae1e8", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Someone moved the little blue chair.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ffc35650196f68bc86ad9fd3c933ded4baf4c6f86a048a2fb5e94b8568df3ad", "generation_seconds_batch": 25.21777619002387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.395919322967529, "genuineness": 4.582659721374512, "identity": 0.27501094341278076, "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_Jealousy_and_Envy/70d66de0f6abc9c3ef9873433aeefd45fca07878807abacb348f0ec598aae1e8.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "70dad5fddd4bebce3bac4424bedebc69a0b297f46d8cdf3e15baee4f2b9f3bf3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1732d818ec51e489c019a0adb9365e35ffc2e65496e6b995ef3d02002c99d8a3", "generation_seconds_batch": 25.722407126100734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.284721851348877, "genuineness": 4.406930446624756, "identity": 0.5523279309272766, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/70dad5fddd4bebce3bac4424bedebc69a0b297f46d8cdf3e15baee4f2b9f3bf3.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "70e92650814cf79e2d9de61fedd0fa3f53f778e3c9699013ce34024572b8a48a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1934733b18ef9abe8e0cf614d2b34621c286aa648c5b468d2a7c713d7a393b49", "generation_seconds_batch": 24.1181965979049, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.6334228515625, "genuineness": 4.532451152801514, "identity": 0.7780040502548218, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/70e92650814cf79e2d9de61fedd0fa3f53f778e3c9699013ce34024572b8a48a.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "70ecb005efd148a381e3d4c0cec12650393357375b24a1ebdab9ddea1cf5440f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cb1f48ce283c2b1799c8fe70096271cb906ed00cc8e5ddc92e42453660e48dcf", "generation_seconds_batch": 23.194389638025314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 5.792276382446289, "genuineness": 4.7458367347717285, "identity": 0.737933874130249, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/70ecb005efd148a381e3d4c0cec12650393357375b24a1ebdab9ddea1cf5440f.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "710745a5e9e1339faee03e7a157a0e2676ea6b0f77fe4bdac828c1919a4dc039", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "653a76cc8dc220538b87f262fd4d6f7d27a55ba568b39448a9546a7ae6c50cb8", "generation_seconds_batch": 25.204237458994612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 4.540312767028809, "genuineness": 3.7542223930358887, "identity": 0.4336000084877014, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/710745a5e9e1339faee03e7a157a0e2676ea6b0f77fe4bdac828c1919a4dc039.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "71200d11e19baa23137ea497cac137c49de70c130ad7e7e6f8849440cf2e214b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30060a27e8144c69da7de42028c24dfe2721c173b3bff401847ad5007fd3cbee", "generation_seconds_batch": 19.20388805202674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.629451274871826, "genuineness": 4.607763767242432, "identity": 0.6397770643234253, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/71200d11e19baa23137ea497cac137c49de70c130ad7e7e6f8849440cf2e214b.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "7162168b0808c566e65385f3f9c625d793c258a2e3d3bd367e77efe564b1d129", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9e0d0e6927579ac3923d67797727d607156723b060245554bffc2f22b5a32188", "generation_seconds_batch": 24.98443908803165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03355531394481659, "target_z": -0.40625001044645787, "ce": 5.474569320678711, "genuineness": 4.080576419830322, "identity": 0.42459768056869507, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7162168b0808c566e65385f3f9c625d793c258a2e3d3bd367e77efe564b1d129.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "71bd12537b88f782e7a9881ec752ab8ccfac09e058d36f790b021152e26b704e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9c4a3d7cec3929db5f448963780fbb41a141344901eea78f33da01f56987f95d", "generation_seconds_batch": 25.890862934058532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 5.839932441711426, "genuineness": 4.519899368286133, "identity": 0.4438124895095825, "hypothesis": "De deur 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_Jealousy_and_Envy/71bd12537b88f782e7a9881ec752ab8ccfac09e058d36f790b021152e26b704e.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": "71d8f80bcb418e5d479b1b748e5719a4f88d169c7aa3dd09fb859364ce4ca7ed", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95ea6b442b3df0ab6deea5de2c757a95cd15ec66c28147a6db681d0228564309", "generation_seconds_batch": 24.88898547796998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05270907282829285, "target_z": -0.3632812387700578, "ce": 5.649308204650879, "genuineness": 4.557555198669434, "identity": 0.6826236844062805, "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_Jealousy_and_Envy/71d8f80bcb418e5d479b1b748e5719a4f88d169c7aa3dd09fb859364ce4ca7ed.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "72077d212381cf771e6803d048b17224192dbf4526e4aee9c33d7fa79501ce60", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c48cc16a35e7c366d209992a7396f0dc4fdb441f61db6deced48ab2643101098", "generation_seconds_batch": 25.131123370025307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.434855937957764, "genuineness": 4.457139015197754, "identity": 0.6344778537750244, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "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_Jealousy_and_Envy/72077d212381cf771e6803d048b17224192dbf4526e4aee9c33d7fa79501ce60.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "72639d095bf88a2a7c7605a02615de02534955cc976ccdc55d60ec8522671744", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8dbea77b95ddc02aeaa2301cbb823a3ffb5e6c2f4d2c814b021911c27719a221", "generation_seconds_batch": 17.935514808050357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.292664527893066, "genuineness": 4.68307638168335, "identity": 0.4229896068572998, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/72639d095bf88a2a7c7605a02615de02534955cc976ccdc55d60ec8522671744.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "72e3743db26353dbfe815054cc50b160e5adf324a3a293505133bc43469eec82", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1420cf1d69cd0ec685dfaaadd6f4d693d64076e8e8ae023aaee9e92185898ccb", "generation_seconds_batch": 24.979949443018995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.434855937957764, "genuineness": 4.149612903594971, "identity": 0.5039633512496948, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/72e3743db26353dbfe815054cc50b160e5adf324a3a293505133bc43469eec82.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "72ece8d410a90c5a980bae75f0e884c7f14767f5d9d112b46bfdf9a4f3889d3f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a67c3e13ecbf3c32f2a5747ddb403c906e510d867c6e821a91f1d32b5889f0a0", "generation_seconds_batch": 24.763674028916284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 6.149696350097656, "genuineness": 4.394378662109375, "identity": 0.6820192933082581, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/72ece8d410a90c5a980bae75f0e884c7f14767f5d9d112b46bfdf9a4f3889d3f.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "733ba8111ce31f45ea63f95933f53b1ab1814ecdceb8ff74463702bccddc2b4e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1308d08fe0214783cd569b169bbc5a5e4212ff1cf9acc9bc4d475ca886e3a560", "generation_seconds_batch": 24.706391585059464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.41180419921875, "genuineness": 4.482243061065674, "identity": 0.4874500036239624, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/733ba8111ce31f45ea63f95933f53b1ab1814ecdceb8ff74463702bccddc2b4e.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "733ed57b9c1de161f17dbc67caf374c600555990c837fd5923562a1d85cb7ff7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "516b91bea0ea56d4145628e3aab5c15787d68b5f9c96c1c250cff793aa526660", "generation_seconds_batch": 18.16060613305308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.054384231567383, "genuineness": 4.306513786315918, "identity": 0.6864089965820312, "hypothesis": "De deur 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_Jealousy_and_Envy/733ed57b9c1de161f17dbc67caf374c600555990c837fd5923562a1d85cb7ff7.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "7454def6d59481cd5f275b0c73f586c941108ba783de71a73d94d8b6ae8c4b1f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "67cc5d62744d46f61e30d488172ad877ded7404c632c2adeb57ca4968c36da1d", "generation_seconds_batch": 26.190702778985724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.967014789581299, "genuineness": 4.425758361816406, "identity": 0.4808066487312317, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7454def6d59481cd5f275b0c73f586c941108ba783de71a73d94d8b6ae8c4b1f.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "74d3edfc2d60cb6deb39003dd609bd26fa9d21b5d331633678e20e314e7cffc3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dc1fdb96c8ffaa9dbfcd195a13f9635de1d7ede7b416d27a9056923125f306b0", "generation_seconds_batch": 23.01861143996939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.3163986802101135, "hypothesis": "The 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_Jealousy_and_Envy/74d3edfc2d60cb6deb39003dd609bd26fa9d21b5d331633678e20e314e7cffc3.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "754d5d254bb48678e070eaf1de3bf0e1e168099d7c7eba5b01e54c4e7c8cbf45", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "24335176b134c1483b3db46a3308965a42a223af2350538fe588fb02f609adea", "generation_seconds_batch": 25.47258988604881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 5.792276382446289, "genuineness": 4.494794845581055, "identity": 0.6649267077445984, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/754d5d254bb48678e070eaf1de3bf0e1e168099d7c7eba5b01e54c4e7c8cbf45.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": "755faed7215ce731b093f86be7e53d5fdf3660093074f55d3ce57545e433aa6f", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3a0bf6e451499d7c303e8d8064941da8a1b9d0da37462ee92fb007504532bc9", "generation_seconds_batch": 30.290494438959286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.0305562019348145, "genuineness": 4.15588903427124, "identity": 0.6913654804229736, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit.", "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_Jealousy_and_Envy/755faed7215ce731b093f86be7e53d5fdf3660093074f55d3ce57545e433aa6f.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "757871279e4b4b5a778d565a911f16857c9eb743aabc9b19a5c9a4ba29afa5bf", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f4901f2899317a9edc653ea59037d0309946af5a7172b87e7a2aac7eccce523", "generation_seconds_batch": 25.36387553298846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.2090122103691101, "hypothesis": "The 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_Jealousy_and_Envy/757871279e4b4b5a778d565a911f16857c9eb743aabc9b19a5c9a4ba29afa5bf.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "75878cbc77f96091f9e22eff20486c6355feb0265ec7ad228ef84f6470792e8e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b4ceb0cbec7af35870512eb33dfb80b2b6a564fbd1d4fd778ad7b56a533d7462", "generation_seconds_batch": 25.12381805595942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 4.748807907104492, "genuineness": 4.105680465698242, "identity": 0.710046112537384, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/75878cbc77f96091f9e22eff20486c6355feb0265ec7ad228ef84f6470792e8e.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "76573b20c17b9cf9700ad7fb80ee9cd66c3b39909d3fc859b4e16046fa8437fe", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "90e531497cbe24902d724a79db70fa3fc4303bfb7017a7233ed309df0edbba6d", "generation_seconds_batch": 17.935514808050357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.221180438995361, "genuineness": 4.444586753845215, "identity": 0.6606048345565796, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/76573b20c17b9cf9700ad7fb80ee9cd66c3b39909d3fc859b4e16046fa8437fe.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": "76a348f695e2cba42d3b267bfeec16a2a3144c72db4f9025c69e919d077ed872", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Your message arrived after I had left.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "151eca3251a8f2b7eac0acf8f0688b87c208f336af58142cfcc131e082d3e268", "generation_seconds_batch": 25.13933424698189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.24500846862793, "genuineness": 4.632867813110352, "identity": 0.3396303057670593, "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_Jealousy_and_Envy/76a348f695e2cba42d3b267bfeec16a2a3144c72db4f9025c69e919d077ed872.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "76ad1f5f13f45eec7ee10ddc8b29fbb986229c572f2b40bdc0ae843400244a29", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3d29aecceecc3e1823c93c8810817817737ec52399d084478b8cf38d5dc5e7f8", "generation_seconds_batch": 30.06650677707512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028331562876701355, "target_z": -0.41796876331923377, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.4416882395744324, "hypothesis": "De deur 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_Jealousy_and_Envy/76ad1f5f13f45eec7ee10ddc8b29fbb986229c572f2b40bdc0ae843400244a29.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "7708b3b0abf67e48e26c80f7acb17441b69d8178d163517458bd43769efd61c7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "23302ebd31acb73ffe4f716d531e4cbc15da53ec15de6029827f05018f48893b", "generation_seconds_batch": 24.763674028916284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.046441555023193, "genuineness": 4.143336772918701, "identity": 0.6207665205001831, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7708b3b0abf67e48e26c80f7acb17441b69d8178d163517458bd43769efd61c7.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1f7006066aee0b8bad9a2451bea149e0d63cccb1b75c05c91c1cabcbc502559", "generation_seconds_batch": 18.331307807005942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.197352409362793, "genuineness": 4.432034492492676, "identity": 0.7341287136077881, "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_Jealousy_and_Envy/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "77a5898cf7464bee2f4e7562a8d16ace72af352882c934915b286ea4fb215650", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b287280c08c135f20b6e03ffd165ad27c8b988eae852c4140ad233d5d95e3ac3", "generation_seconds_batch": 18.95955078897532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.967014789581299, "genuineness": 4.570107460021973, "identity": 0.6796755790710449, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/77a5898cf7464bee2f4e7562a8d16ace72af352882c934915b286ea4fb215650.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "77ae0b585b912a7917ad7dbfbdcb712a05b41a08ef9d72716a1a19706258b624", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "90cea93fc6da95ef343158e3abee4a89795a065d571098438b6ca127fb560eb0", "generation_seconds_batch": 25.727097783004865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 5.510311126708984, "genuineness": 4.519899368286133, "identity": 0.5579937696456909, "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_Jealousy_and_Envy/77ae0b585b912a7917ad7dbfbdcb712a05b41a08ef9d72716a1a19706258b624.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "77dfe5ecdbeaf78c998acab78f3ab2301b04aa58a313b4d254e071c3a17a2fa6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "27d2124e88af1ba0d493a810d5a869e80cc830aaf3e24aa6b6c5ba1448bc2532", "generation_seconds_batch": 18.951766718993895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005622804164886475, "target_z": -0.49414062356361205, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.8264087438583374, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/77dfe5ecdbeaf78c998acab78f3ab2301b04aa58a313b4d254e071c3a17a2fa6.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "77f086b7ee01c227f1ea920a3ae76a26a7be6a9824da357dad8dfc8b7c120bc8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5688682759d2a463be47b832aca1a1f31079f205e34384c85dc09199b6abb64", "generation_seconds_batch": 24.89510673901532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.372091293334961, "genuineness": 4.394378662109375, "identity": 0.4613816738128662, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/77f086b7ee01c227f1ea920a3ae76a26a7be6a9824da357dad8dfc8b7c120bc8.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": "77f44ec076536b79a9d21cbcd701670dec6a95392195632e3d2d2fd6322ae1e8", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "0b77060597a410ada6d8d46a3f97b2d08aebdd01f05947efacfd5f0b681b5a3f", "generation_seconds_batch": 20.73326841101516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 5.959072113037109, "genuineness": 4.3127899169921875, "identity": 0.7110610604286194, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug uit.", "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_Jealousy_and_Envy/77f44ec076536b79a9d21cbcd701670dec6a95392195632e3d2d2fd6322ae1e8.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "784ce20a731650a6324d63df6b3e4ea79a71748fd1540eee04fb567ef9ed262d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6707f6d146f56df00c60fac225ebb50a3c962bb785c0ef1e75dc9921d1182eb7", "generation_seconds_batch": 23.64291230100207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.213237762451172, "genuineness": 4.293961524963379, "identity": 0.38945814967155457, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/784ce20a731650a6324d63df6b3e4ea79a71748fd1540eee04fb567ef9ed262d.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "124ae60329e9dfaff8e921c945d893dabf897206dd3de48a896ea89f0665ec4f", "generation_seconds_batch": 17.420003319042735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.09409761428833, "genuineness": 4.444586753845215, "identity": 0.6193418502807617, "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_Jealousy_and_Envy/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "79652497ae284d4b9e642e91510607ad3db7e53eb76b20a1854487cc0ccc526b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a350759c55cb54bce13bd821281c9b1e1dd2db99497a701614baba3c5d91633c", "generation_seconds_batch": 24.706391585059464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.23706579208374, "genuineness": 3.9299514293670654, "identity": 0.5409847497940063, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/79652497ae284d4b9e642e91510607ad3db7e53eb76b20a1854487cc0ccc526b.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "798ddeac4c72ea00893aac4010dca4520f1a3133a44784bfd0b01e1a4e1404c4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7142885c40f6f9f582d5bec73f510c0bd5b89f68c2b31575cbaed60ae276ac4c", "generation_seconds_batch": 27.1141992630437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 5.673136234283447, "genuineness": 4.7332844734191895, "identity": 0.6954190731048584, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/798ddeac4c72ea00893aac4010dca4520f1a3133a44784bfd0b01e1a4e1404c4.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "79ef792b1b5a6084295cad17c2de4972122da16a488c9dc33210c9e364b1a301", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5416ca8bc2ded78ba28d1cb4a8246ae3bda33626ef625eeea3e36162e72ee3f6", "generation_seconds_batch": 27.319235270959325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.760505676269531, "genuineness": 4.356721878051758, "identity": 0.19407594203948975, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/79ef792b1b5a6084295cad17c2de4972122da16a488c9dc33210c9e364b1a301.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "7a07ff9ee1ca4801776646e7c85ceaaaf8326ae540f0bfb915dc007368ae400f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "746b852b46d0c4f5b8545f046d9b5f96d94fd5e82d21903cfc3692b557f435fa", "generation_seconds_batch": 25.7998307159869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.816103935241699, "genuineness": 4.432034492492676, "identity": 0.7243697643280029, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7a07ff9ee1ca4801776646e7c85ceaaaf8326ae540f0bfb915dc007368ae400f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "7a3c7290499a5644afcb3155e4724d41a26d7663fa168d92a8924e79374e9fc0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0862142f8f1d33994666ee8828cf160bd5965b798bdcf626601b9d82ccdb272f", "generation_seconds_batch": 19.402034858008847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.824047088623047, "genuineness": 4.68307638168335, "identity": 0.7335975170135498, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7a3c7290499a5644afcb3155e4724d41a26d7663fa168d92a8924e79374e9fc0.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": "7a3f58cafdf6ebbc1c6c948c0fd325c18b2229f7c47766049204034429dcb670", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The keys are on the kitchen table.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "e6af678d1211782e7158b7cacd5beb33437ad8e2199ad7fa67cbda981c6dbb0a", "generation_seconds_batch": 18.989632124081254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.062326908111572, "genuineness": 4.3504462242126465, "identity": 0.27528852224349976, "hypothesis": "The keys are on the kitchen table. I checked the drawer and 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_Jealousy_and_Envy/7a3f58cafdf6ebbc1c6c948c0fd325c18b2229f7c47766049204034429dcb670.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "7ab08d0c710881f99ce5e52d4c5143d6d551f6e27a91a3aae44bf6241b860254", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d79fbb42953ac77e2350c7f7b928d1a995b69a3a8ce6bc930f3a1aac861d367c", "generation_seconds_batch": 19.534236458013766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 5.7406487464904785, "genuineness": 4.570107460021973, "identity": 0.6030797362327576, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7ab08d0c710881f99ce5e52d4c5143d6d551f6e27a91a3aae44bf6241b860254.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "7ae70f686546a3f41ff622d9da982154edbb311a9380164bd337d6ee9312d1ed", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d550d839633501b3375be1f93ef68df5f073400d6e542d1b1e030061a64b20f", "generation_seconds_batch": 25.47258988604881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 5.506340026855469, "genuineness": 4.507347106933594, "identity": 0.6868482828140259, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7ae70f686546a3f41ff622d9da982154edbb311a9380164bd337d6ee9312d1ed.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "7b6604081bc11775cfaeaa6966cca1e72a9cc9d04878ef034f5a36e37e2f19ff", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9d01ac67365a0579b8f0da39f6062792323d0762cacae72eb4d2afe105026894", "generation_seconds_batch": 25.065250448067673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.200547218322754, "genuineness": 4.055472373962402, "identity": 0.51615971326828, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7b6604081bc11775cfaeaa6966cca1e72a9cc9d04878ef034f5a36e37e2f19ff.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "7b92e111b4532b61e38ce35dd8cbd5a7eb2b1696a57bc20523c2eb96e3fc34d7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3b13053fcba5eeda2382a0d6f89fb0313b7bc09abf8b9b77f7b6b7650e746267", "generation_seconds_batch": 27.276028541033156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.046441555023193, "genuineness": 4.268857479095459, "identity": 0.7031128406524658, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7b92e111b4532b61e38ce35dd8cbd5a7eb2b1696a57bc20523c2eb96e3fc34d7.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "7bf9a877f9d68f84f3d73783fda0f92b5a93705c5206c84e19dad6f61abd3000", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ac859b59ce6ac302440da3bdf228ffa23f53492ab7c810c24690b946ffff4e31", "generation_seconds_batch": 24.744648523977958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.054384231567383, "genuineness": 4.65797233581543, "identity": 0.7062292098999023, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7bf9a877f9d68f84f3d73783fda0f92b5a93705c5206c84e19dad6f61abd3000.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "7c3e5f3a651e934a6986669cc42606c089102c30dcd041c818689a12879c58e4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a9cd824b056b84ea97fee073f60d80383e6db5e8a8f78d1131e2e42d76fb2074", "generation_seconds_batch": 25.368129769922234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.300607204437256, "genuineness": 4.3881025314331055, "identity": 0.2855624556541443, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7c3e5f3a651e934a6986669cc42606c089102c30dcd041c818689a12879c58e4.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "7c51e186147d3e8bce4a4f791a6cc5019f1a3de17d8c59371ba5008a473b37d3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "495fd5018b1a0d1cc6460a144a8ca5785bbfda66d0fcec2d7dfe781708cdeecc", "generation_seconds_batch": 19.081560063990764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 5.935244083404541, "genuineness": 4.7458367347717285, "identity": 0.6649038195610046, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7c51e186147d3e8bce4a4f791a6cc5019f1a3de17d8c59371ba5008a473b37d3.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "7d498083914c3763359f1a4192e886ed5224dbbee365e8af0b087523b867b6da", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "97734bb3397bcd24903b5e7c2bb7378b3109b44718c537d7e87ce88cd773fd9f", "generation_seconds_batch": 25.566797500941902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 5.998785495758057, "genuineness": 4.482243061065674, "identity": 0.6095942258834839, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7d498083914c3763359f1a4192e886ed5224dbbee365e8af0b087523b867b6da.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "7d7b7047ce82619b20cd7f96003c92492fb228736a108d93b4c8c89d951dd4ba", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1a631fc151272af2cf6648818c8059a7bf238160dae416b6cd611c5f12f232fd", "generation_seconds_batch": 25.74961236899253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.0305562019348145, "genuineness": 4.632867813110352, "identity": 0.8121256828308105, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7d7b7047ce82619b20cd7f96003c92492fb228736a108d93b4c8c89d951dd4ba.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "7de687cc664f53b50611977714c8c26e5aea50d7894eb0f2439e8bbb301347ec", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9c50b2d8afc527c195c404217f08eef3090ff8161fa33c8bee2438afd792305e", "generation_seconds_batch": 17.4569014509907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 5.831989288330078, "genuineness": 4.6203155517578125, "identity": 0.5115374326705933, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7de687cc664f53b50611977714c8c26e5aea50d7894eb0f2439e8bbb301347ec.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "7e249fc8aa5ca9b4b80890ab7e5c30f687ebef06c04f032f9d9d5f8fd780c81b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "737393df44aeae167ac33b4cd0d6ac4db6dc8fd1bd0c6094658177a3f8f47d21", "generation_seconds_batch": 27.220291959005408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 5.871703147888184, "genuineness": 4.344170093536377, "identity": 0.6351209878921509, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7e249fc8aa5ca9b4b80890ab7e5c30f687ebef06c04f032f9d9d5f8fd780c81b.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "7ea0f70db073de6a5f4d92b23d713e937623a5a0d5a8ad4c05c16d85e4b01936", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a93232e24e9a8b7a93b64c69f04356c6dd9e8ac648795d245dda43fa892401a", "generation_seconds_batch": 20.76800848497078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 5.847874641418457, "genuineness": 4.306513786315918, "identity": 0.26215797662734985, "hypothesis": "The 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_Jealousy_and_Envy/7ea0f70db073de6a5f4d92b23d713e937623a5a0d5a8ad4c05c16d85e4b01936.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "7ed744c6e0aec21c21a63d5f649bf0dfc71b4ea4b768d163e04d82148f5720d1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "75db233b8e044a52b82b36ded9963d98569e2333cc9df461d6c180e6fcf481f5", "generation_seconds_batch": 18.491391427000053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02042342722415924, "target_z": -0.5273437455602554, "ce": 6.332377910614014, "genuineness": 4.268857479095459, "identity": 0.32531318068504333, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7ed744c6e0aec21c21a63d5f649bf0dfc71b4ea4b768d163e04d82148f5720d1.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "7ee4bd4aca2d62a48a5ae1e957ab96808271fc150f24695ff3a5465507050c4b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f84b5836dadc35b1e33174167c697bcef5489e42a26f686effd5b778df3cfed1", "generation_seconds_batch": 19.691760155954398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.959072113037109, "genuineness": 4.419482707977295, "identity": 0.7538076639175415, "hypothesis": "De deur 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_Jealousy_and_Envy/7ee4bd4aca2d62a48a5ae1e957ab96808271fc150f24695ff3a5465507050c4b.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "7f45c30c5ac6639b71ff39c7bbf6a89feeb22e30448d34f8979f74ddf8230952", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e22afd589316a34e996ac5c7664445c4268af99fac174744925db27bfa842560", "generation_seconds_batch": 26.75653860392049, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.4912309646606445, "genuineness": 4.444586753845215, "identity": 0.3073889911174774, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/7f45c30c5ac6639b71ff39c7bbf6a89feeb22e30448d34f8979f74ddf8230952.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "55f465eba6993f06ac7efee6e8138311f19bc709076fe1c89ff583503a8886c8", "generation_seconds_batch": 17.553626246983185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.348263263702393, "genuineness": 4.507347106933594, "identity": 0.3641439378261566, "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_Jealousy_and_Envy/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "80124be179b17aa28b2ec26299249d2f44b184620c9283a59052d916a22d0208", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "75f5a32375dd725201f625d0d4f3cf876fb556038226c58ad05bb715c35d78c5", "generation_seconds_batch": 23.33064280904364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 6.125868320465088, "genuineness": 4.595211505889893, "identity": 0.7385640740394592, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/80124be179b17aa28b2ec26299249d2f44b184620c9283a59052d916a22d0208.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "8031dce749200b516a2089dba5619183dee191fcdf7eac3ab1d0dbe48ec43152", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "536197cb2950e02b167170d271982adeb473ed1134bfdcc9c9c0a1a6c3e34c11", "generation_seconds_batch": 25.560263633960858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 6.109982967376709, "genuineness": 4.457139015197754, "identity": 0.6740255355834961, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8031dce749200b516a2089dba5619183dee191fcdf7eac3ab1d0dbe48ec43152.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "806b20f18aca7cbfc6754476c294781dc2ad48ce676a303a478df265b52ab2a3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a3558d89dbd024619717dba7df045df9c87c0be489a0cc8e8885df2841590680", "generation_seconds_batch": 18.41673662106041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 5.903473377227783, "genuineness": 4.337893962860107, "identity": 0.7226440906524658, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/806b20f18aca7cbfc6754476c294781dc2ad48ce676a303a478df265b52ab2a3.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "10d5b31d0fe03a2609faa92c468d22ddd8ea23a8b5f043ff0d30a9f1cc283b4e", "generation_seconds_batch": 20.12810609000735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.356205940246582, "genuineness": 4.582659721374512, "identity": 0.6269530057907104, "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_Jealousy_and_Envy/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "80da1d618841ec36f84bf73c1f1da55584a0a3d2531052abf1c3fce80f5c1e55", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "378b7d0b4da0428b76e3e12d80330aca505508bfc29c4317d507f5553f481a49", "generation_seconds_batch": 25.204237458994612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025719687342643738, "target_z": -0.4238281397556217, "ce": 4.875393867492676, "genuineness": 4.281409740447998, "identity": 0.6170306205749512, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/80da1d618841ec36f84bf73c1f1da55584a0a3d2531052abf1c3fce80f5c1e55.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "81246e9eb945b809e71fdab01b92d60501ccefecdaaa1461dfc1e850066f3b97", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7a6895d75a050feeca68b5db97e1164ea3e5d7196388761bbb5f9287136d029f", "generation_seconds_batch": 23.182550720055588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.006728172302246, "genuineness": 4.720732688903809, "identity": 0.7188787460327148, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/81246e9eb945b809e71fdab01b92d60501ccefecdaaa1461dfc1e850066f3b97.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": "814002dda95d8e844ad14de140f7e8ace14aacf7d38b1b47212cda86e230a14d", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "247a2b44f534d19b95b51deca54367173b7c9f981bb548f55fa5386d07642a7d", "generation_seconds_batch": 18.444944615010172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04226157069206238, "target_z": -0.3867187445156096, "ce": 6.0146708488464355, "genuineness": 4.607763767242432, "identity": 0.7906550168991089, "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_Jealousy_and_Envy/814002dda95d8e844ad14de140f7e8ace14aacf7d38b1b47212cda86e230a14d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "81c0abd70681fd0d7e8a84c60d8431420c0e2c7597425ddbcd0fddb9c24289bf", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fc3b15078549233a0d8a9078d157c5dc5958ac08d3363b5b00dd818c20672bc1", "generation_seconds_batch": 23.60728953103535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.5272594690322876, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/81c0abd70681fd0d7e8a84c60d8431420c0e2c7597425ddbcd0fddb9c24289bf.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "81c756714a6216d25255e76182d29fd5978f8ca46318043e1e86aacf594f5fb7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c7386b1c9da1a53060f242e18f4eb8b8ab0d11b51d9f8cd7f14105a965546ee7", "generation_seconds_batch": 19.402034858008847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 6.157639026641846, "genuineness": 4.632867813110352, "identity": 0.565056562423706, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/81c756714a6216d25255e76182d29fd5978f8ca46318043e1e86aacf594f5fb7.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "81ef2816f9451605c0ced35d0024f62c097c240ce48cbae4651c4b528628bb7a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "21d63e0d658084bdf516b2c5d4bfbc373db0ecacdda73c0cd57f7951268893cb", "generation_seconds_batch": 19.82128885993734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.649308204650879, "genuineness": 4.507347106933594, "identity": 0.7109352350234985, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/81ef2816f9451605c0ced35d0024f62c097c240ce48cbae4651c4b528628bb7a.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "82072a5793e3a59cca3ae98aa75a9fca0a5d69cc06625a1f06e092c0eead197b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ecd2277453eac28a85e5ef722a26bf1a8a1035c1614e271dd9577c88bfbeb0b7", "generation_seconds_batch": 17.4569014509907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.534139156341553, "genuineness": 4.344170093536377, "identity": 0.6777817010879517, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/82072a5793e3a59cca3ae98aa75a9fca0a5d69cc06625a1f06e092c0eead197b.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "825050aa7831bcf19c708caa07413a7c89276235f1b991f8481f377c3a144d83", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6d03db921c398899ccc9706e6317f7f859b820c57c6392e8b5af6fe52d5bf036", "generation_seconds_batch": 25.834864537930116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.022613525390625, "genuineness": 4.557555198669434, "identity": 0.7494525909423828, "hypothesis": "De deur 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_Jealousy_and_Envy/825050aa7831bcf19c708caa07413a7c89276235f1b991f8481f377c3a144d83.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "832258fc4ef1f60db7b24083aa6c01b0ee3601dae45ce3fc8bf87229eeb009ad", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "09a5f8200dfd06e374532e9cf6ac8c3320442d44e5ef118a86517a5011d422b4", "generation_seconds_batch": 25.647324160090648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 6.165581703186035, "genuineness": 4.532451152801514, "identity": 0.6905785799026489, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/832258fc4ef1f60db7b24083aa6c01b0ee3601dae45ce3fc8bf87229eeb009ad.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "83d62a5407d99c4aa1ef325f8a14cac22145766b7c0c5ceb33af5ae86339a70c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "94d8804aaf2fb1a054f06946c02fe75a4018fa4a4f0614d0d25b830cfe04494f", "generation_seconds_batch": 25.170651655993424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030943438410758972, "target_z": -0.4121093868828458, "ce": 6.086154937744141, "genuineness": 4.068024158477783, "identity": 0.46307188272476196, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/83d62a5407d99c4aa1ef325f8a14cac22145766b7c0c5ceb33af5ae86339a70c.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "83e8ac62902cf40260dcdf27c5e9ed68272391d3e36543bc483414c29132c2ec", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2a273ef3c240096e3bb2b67e4c0f3ceefdf5a6e0acbe9ea92e2c131a0ecfcbf5", "generation_seconds_batch": 24.107758676982485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.7637985944747925, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/83e8ac62902cf40260dcdf27c5e9ed68272391d3e36543bc483414c29132c2ec.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "8471eda9214fe1e6d1b8d5e07f06967a7a7182c2a277225e390af373f6f49d22", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "781a92484fc266d1857690f0a0190f726cfc51a7c961eb11580b27b4d56bc623", "generation_seconds_batch": 19.490630768006667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 5.895530700683594, "genuineness": 4.482243061065674, "identity": 0.5628596544265747, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8471eda9214fe1e6d1b8d5e07f06967a7a7182c2a277225e390af373f6f49d22.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "847789feada1041ced7daae76e99de981ffb185b57386e6f66a44ec5bfc1289d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6363ab31d0b476df3406d457f82b01df7fd82e7e52c301c09e1d2c4200ca2945", "generation_seconds_batch": 27.319235270959325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.959072113037109, "genuineness": 4.331617832183838, "identity": 0.4939468204975128, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/847789feada1041ced7daae76e99de981ffb185b57386e6f66a44ec5bfc1289d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "84d257979d82636eafa6522ec398e559640b1ca5244c40f53245860ba0a16fb6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "879a5fd66ba8be0eb6f68a09d1a47f7e608a18fac52505829faaedba97d0aa54", "generation_seconds_batch": 26.719967841054313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.990842819213867, "genuineness": 4.519899368286133, "identity": 0.571161150932312, "hypothesis": "De deur 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_Jealousy_and_Envy/84d257979d82636eafa6522ec398e559640b1ca5244c40f53245860ba0a16fb6.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": "85404f17d91b5f15317d2f618f7b362e875f4aa478c9217bf54d46da21c649d6", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "1441ded6c7c0b07f6c36324af6d77bfeb6875297cfb0be2b6210fa74846d0b91", "generation_seconds_batch": 19.239313781959936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.09409761428833, "genuineness": 4.833701133728027, "identity": 0.7997690439224243, "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_Jealousy_and_Envy/85404f17d91b5f15317d2f618f7b362e875f4aa478c9217bf54d46da21c649d6.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "8575598d96cd9ce2f353e10a58b582b2afc50f5144e45181e082edd20535a6ba", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "040a8a4758777015bcf6a9de3f7532e28117a35d72214ad4dc11ad85510db903", "generation_seconds_batch": 25.810610112035647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.689021587371826, "genuineness": 4.607763767242432, "identity": 0.8499001860618591, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8575598d96cd9ce2f353e10a58b582b2afc50f5144e45181e082edd20535a6ba.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "857c4e670c6acf385e68d57783c4a3a55f3e7e0c4cf4f7f2da9150ebcadd919f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a6da04b13ae5f3cce374151ff3cca8d4db60781e7a29f77dee0bd5215babd688", "generation_seconds_batch": 24.99562331789639, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.173524379730225, "genuineness": 4.13078498840332, "identity": 0.24924634397029877, "hypothesis": "The 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_Jealousy_and_Envy/857c4e670c6acf385e68d57783c4a3a55f3e7e0c4cf4f7f2da9150ebcadd919f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "85a7d37033df229ed157c09ba8509d91bc6685012f538b67fae690208752edae", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1dff13270b7282d640dfce6dfd247f3cd41aee10d9a5736cafcdba51871763e8", "generation_seconds_batch": 24.790520512964576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.229123115539551, "genuineness": 4.808597087860107, "identity": 0.6694455146789551, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/85a7d37033df229ed157c09ba8509d91bc6685012f538b67fae690208752edae.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "85c4aadc7f348e8ce4ab31860dfd7ecedb37ddf460bbc2edba221fb66fe37cdc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "adbaef01331d788fb367361b4f1314c512f52b9fe8d5516b43161b9a53200840", "generation_seconds_batch": 26.893575283000246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 5.617537498474121, "genuineness": 4.457139015197754, "identity": 0.6574059724807739, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/85c4aadc7f348e8ce4ab31860dfd7ecedb37ddf460bbc2edba221fb66fe37cdc.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "85d89073638ae6732518ef20f93f18b4215ca2fb59de80fe060b1e659ccac4fb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af0992c2a2916462bf0dab9671257b35cbfc9c8499ff4f8dbfc642c858a360ec", "generation_seconds_batch": 25.45057526405435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.229123115539551, "genuineness": 4.337893962860107, "identity": 0.36075296998023987, "hypothesis": "The 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_Jealousy_and_Envy/85d89073638ae6732518ef20f93f18b4215ca2fb59de80fe060b1e659ccac4fb.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "867cb9f5687765575a217e2c8f9dd0b11a926ce9ab1bdb273a9cf7441e2c6204", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a0f701533d28a97645b869da7cade3b75b7d615d0979ec67c0b5587c997ec782", "generation_seconds_batch": 17.930450039100833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 5.498397350311279, "genuineness": 4.413206577301025, "identity": 0.6861270070075989, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/867cb9f5687765575a217e2c8f9dd0b11a926ce9ab1bdb273a9cf7441e2c6204.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "868ac657957f3241aa5dcfeff9e4051e842bb10deb70837094d8acb560bf27f5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2ee25a9a0aa8351458ba97395ee4f63f5a18d5ab91ec3c7af48ed92559f41a76", "generation_seconds_batch": 27.837132548098452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.006728172302246, "genuineness": 4.582659721374512, "identity": 0.5918278694152832, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/868ac657957f3241aa5dcfeff9e4051e842bb10deb70837094d8acb560bf27f5.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "86f8fefdb98e9928a46ace4d7a67a57cbf16e5159e0aca80eaf6572e016649be", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "92d7b773f0d8ac9c12fda23015a7a286f6704acd16b3230f706d97e5deb5e952", "generation_seconds_batch": 19.081560063990764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.09409761428833, "genuineness": 4.770940780639648, "identity": 0.6540267467498779, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/86f8fefdb98e9928a46ace4d7a67a57cbf16e5159e0aca80eaf6572e016649be.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "870e2d48774df875a3e603b1c5fa54d3549f24762230640f4e9ec75980d30ed3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8707d9c5d8b892dba18af1b5d3d4d5668d773fd252e93efe4c3a92bb4feff9c4", "generation_seconds_batch": 24.95846275705844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.518253803253174, "genuineness": 4.570107460021973, "identity": 0.6126183271408081, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/870e2d48774df875a3e603b1c5fa54d3549f24762230640f4e9ec75980d30ed3.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "8749790b220f7eb69447da1070ac3fe98beab0be27bfe5552f2de74d4bbd7362", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0bbd466147f19219f82bf4243f86a64f0058378976b855cd6cd148ac73d02234", "generation_seconds_batch": 24.859505741042085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 6.022613525390625, "genuineness": 4.519899368286133, "identity": 0.5139662623405457, "hypothesis": "De deur 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_Jealousy_and_Envy/8749790b220f7eb69447da1070ac3fe98beab0be27bfe5552f2de74d4bbd7362.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "87c856b88215338aa6d99f6791bf80a1833eb9a878a72910463d6c7d730ce09a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1e14730c243e3246f4fc88356fee62ffbf1c8af83fe9fcadca23b7d70db53bbd", "generation_seconds_batch": 17.64128833496943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.24917875230312347, "hypothesis": "De deur 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_Jealousy_and_Envy/87c856b88215338aa6d99f6791bf80a1833eb9a878a72910463d6c7d730ce09a.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": "88e1582a98105b5062914b32544e616e2f4eec87a39f3112ca69252d8a0746bb", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7bc1f1f2abbabf2174d1d5186ab186e0d06c3b710fd06ae3e35f7b244953b30", "generation_seconds_batch": 25.530161113012582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0405203253030777, "target_z": -0.3906249843303132, "ce": 5.982900142669678, "genuineness": 4.7834930419921875, "identity": 0.7196093797683716, "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_Jealousy_and_Envy/88e1582a98105b5062914b32544e616e2f4eec87a39f3112ca69252d8a0746bb.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "891ceb499427b0625fa56a6252f322529bbaaa9b2a5aebe7a89d03ff3d7cca5e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f6204d75d30d60b77c32f64efbbbb65eb77463b0b7366a606c6f23865bf49a01", "generation_seconds_batch": 19.717079291003756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.006728172302246, "genuineness": 4.174716949462891, "identity": 0.5476384162902832, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/891ceb499427b0625fa56a6252f322529bbaaa9b2a5aebe7a89d03ff3d7cca5e.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "8949085527cf5b1751cfc80ff140bd5f303c419d141cbb4559124cd70ecf6295", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b48a657f4dab00f95559fd460275f53105487c3d46956a0d10e7475c27da413f", "generation_seconds_batch": 25.370437199017033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.95112943649292, "genuineness": 4.758388519287109, "identity": 0.7222447395324707, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8949085527cf5b1751cfc80ff140bd5f303c419d141cbb4559124cd70ecf6295.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "8a27cfb06afcca0b8147ee399d6c845c56a3664cfbca07a0721788afa32507b4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ae76dc12c77227ce2d8ec139f66ba13350ab47660c2c27c576f4d4d457bbd75c", "generation_seconds_batch": 19.089124080026522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.109982967376709, "genuineness": 4.068024158477783, "identity": 0.1288861781358719, "hypothesis": "The 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_Jealousy_and_Envy/8a27cfb06afcca0b8147ee399d6c845c56a3664cfbca07a0721788afa32507b4.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "8a280ca746feef806738fc98e21caa2c9f19de1856289a52cd1ef91fe926e09b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7bf86fb8505c1e7cfb6dc47c4370a9359f634d22e01cd3e2d0caab31cca545a8", "generation_seconds_batch": 26.678789766971022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 6.0305562019348145, "genuineness": 4.337893962860107, "identity": 0.605059027671814, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8a280ca746feef806738fc98e21caa2c9f19de1856289a52cd1ef91fe926e09b.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "8a9dc695fef2b3e78c08ffeda90872661aa6b70eee829a3d9f32e3dd9ae94cf5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "284cece0ba6dc1ebd152867b6e36c2f1c46767182f4fa9291d278d2108021cef", "generation_seconds_batch": 18.86279111704789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.046441555023193, "genuineness": 4.65797233581543, "identity": 0.6432508826255798, "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_Jealousy_and_Envy/8a9dc695fef2b3e78c08ffeda90872661aa6b70eee829a3d9f32e3dd9ae94cf5.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": "8ae78fe5325ba281742d739b0e34b99fff1282674ca1bc9638c0a3dab1805929", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "585c6d97a8e7a7349377ebc163f11ff600caf0068e3647edcb65f7edeff7d8af", "generation_seconds_batch": 25.457687178975902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 5.597680568695068, "genuineness": 4.570107460021973, "identity": 0.7400150895118713, "hypothesis": "Celka deplacé la petite chaise bleue Eletis près de la grande bibliothèque. Nous la remetrons après le dejeuner.", "wer": 0.38095238095238093, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8ae78fe5325ba281742d739b0e34b99fff1282674ca1bc9638c0a3dab1805929.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "8ae971b93083d293ba812b4ca2256409f6ddebb568e6840ffae9ad9570a78120", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69958918452a71fd7e03c4a977f5f604cf0fc448d8dce7720eb6b901c385bfb3", "generation_seconds_batch": 25.765534614911303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 6.086154937744141, "genuineness": 4.6203155517578125, "identity": 0.29383575916290283, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8ae971b93083d293ba812b4ca2256409f6ddebb568e6840ffae9ad9570a78120.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "8b388883d9ce65400c014907f1eb7be429061d1b3bc9654bc3709efdced07979", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bc1eee0a6222b93ea66e5c830464380f01914e561844e8df3f0823a5affbdf48", "generation_seconds_batch": 17.170765534974635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.593709468841553, "genuineness": 4.042920112609863, "identity": 0.4913250505924225, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8b388883d9ce65400c014907f1eb7be429061d1b3bc9654bc3709efdced07979.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "8b42a21fd3b8377c062329c6e9409f15a231aaed87d8a0f835629cf1ea83f454", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b8e3cc4095f4339bd9e9181aa2afc45c9fe45c6a026ce63e1d877823489f427e", "generation_seconds_batch": 24.2445097140735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.284721851348877, "genuineness": 4.457139015197754, "identity": 0.722236692905426, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8b42a21fd3b8377c062329c6e9409f15a231aaed87d8a0f835629cf1ea83f454.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "8b4a8cb81b9bbef2300d2012ef2d048ca7b931b3ec484d025c6d5b3fefb3c3dc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a00e50bf654b034abc9aa87e31d5e5a16369b1a44f34da1f23859d338abc06ad", "generation_seconds_batch": 28.697127102059312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.221180438995361, "genuineness": 4.65797233581543, "identity": 0.2404903918504715, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8b4a8cb81b9bbef2300d2012ef2d048ca7b931b3ec484d025c6d5b3fefb3c3dc.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "8bb811e0cbfef6246dc0ae969753944e928f7c69806fdbb0d7451cf4c5501b27", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fbf9b3765148a27c2ba0f5175b3c72c91a3d46a60b9731b600ffc18f320bfc51", "generation_seconds_batch": 26.933353058993816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.09409761428833, "genuineness": 4.545003414154053, "identity": 0.5750678777694702, "hypothesis": "De deur 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_Jealousy_and_Envy/8bb811e0cbfef6246dc0ae969753944e928f7c69806fdbb0d7451cf4c5501b27.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "8bfcd2f8f721d2c6f7fb34870c3c912ccf7db2a97ab780e714765b54f210d65d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ed3054c0b4fd7b333381978695f3bfc29caf8cc88d65c9ea05729eb1d8b98eb", "generation_seconds_batch": 25.493456746917218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.09409761428833, "genuineness": 4.281409740447998, "identity": 0.20163145661354065, "hypothesis": "The 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_Jealousy_and_Envy/8bfcd2f8f721d2c6f7fb34870c3c912ccf7db2a97ab780e714765b54f210d65d.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "8c4fe068309bf126b3ab61eb1953cc44e5450f888d82e7af8a47bcb395381916", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fb445ccb6b237e473201ee2950af3fa602261f8face102f20223d95161aba2da", "generation_seconds_batch": 26.56543734599836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 5.7684478759765625, "genuineness": 4.432034492492676, "identity": 0.6818822622299194, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8c4fe068309bf126b3ab61eb1953cc44e5450f888d82e7af8a47bcb395381916.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "8cc8ccd5e72ad242e773c21bcaa34cf9cef7903bf9ba8cafc615f6d6f7b6152a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "75ecd09e9842d33393e57796e2e834718c8643914c2071f25f6e4fbd36ccbdd9", "generation_seconds_batch": 24.450977499014698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.38003396987915, "genuineness": 4.369274139404297, "identity": 0.6563374400138855, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8cc8ccd5e72ad242e773c21bcaa34cf9cef7903bf9ba8cafc615f6d6f7b6152a.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": "8cdd1dfbcbb05b555a523028379b40da28006ca97482fabd02dd834d6e951c24", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "9de93f47832087e5047dfd0892b44ebaaac576695549e7e9f27fa8524b32cde2", "generation_seconds_batch": 18.767719274037518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.086154937744141, "genuineness": 4.632867813110352, "identity": 0.5112200975418091, "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_Jealousy_and_Envy/8cdd1dfbcbb05b555a523028379b40da28006ca97482fabd02dd834d6e951c24.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "8d105e7500810086260ee35be538b43e81ead07080e80c484646f5b821be25f9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fa380844ab41287c3c2e5a72e2daf5c610b3ab092d70617cfc57f8791d2b1e48", "generation_seconds_batch": 27.276028541033156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.998785495758057, "genuineness": 4.507347106933594, "identity": 0.6210306286811829, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8d105e7500810086260ee35be538b43e81ead07080e80c484646f5b821be25f9.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "8d409485a1b4c0d91f791157c999986f2a430a099517eab84c0e6682b09b39c3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e66eb8ada1d31afe2a1dfc65ac956191eec5da71e34a1ab131f9b7a3307b10a4", "generation_seconds_batch": 23.12684530497063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 5.998785495758057, "genuineness": 4.457139015197754, "identity": 0.6332433223724365, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8d409485a1b4c0d91f791157c999986f2a430a099517eab84c0e6682b09b39c3.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "8d6b12184aadc5b59b86dc3051e0d24563a13874468489ad4ad31f3f1ca1bd4c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3e29f7e50631332b4b2ff0ef8ea8974bd98969a2c75b2b7fd16e279c3bc4daae", "generation_seconds_batch": 24.61580934689846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.252951145172119, "genuineness": 4.005263805389404, "identity": 0.37860825657844543, "hypothesis": "The 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_Jealousy_and_Envy/8d6b12184aadc5b59b86dc3051e0d24563a13874468489ad4ad31f3f1ca1bd4c.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "8d78ccb12df7323abb5c2efddb9a0b43b814cb3c333d3833045a646109f25c45", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9c4396badef918397eba374537244181c7b9253d0c0dc3858845134079e9d1f9", "generation_seconds_batch": 29.463313655927777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 6.054384231567383, "genuineness": 4.570107460021973, "identity": 0.5876449346542358, "hypothesis": "De deur 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_Jealousy_and_Envy/8d78ccb12df7323abb5c2efddb9a0b43b814cb3c333d3833045a646109f25c45.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "8e6eed06b5387c579e068c971350bd4806615d04216d0957ccae03ed7d043df9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "967f628f70afd5bccddf86f9c46c844c202061ce36f4df2bd235f7eb55a4d48a", "generation_seconds_batch": 19.089124080026522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.117925643920898, "genuineness": 3.9927117824554443, "identity": 0.2391335815191269, "hypothesis": "The 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_Jealousy_and_Envy/8e6eed06b5387c579e068c971350bd4806615d04216d0957ccae03ed7d043df9.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "8e9b631a4b5d43511b8c562d2ca786e42fad75da274b4949bc605afb7e0efc27", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fa41aabfa92cf9c32b0219dd92a0f49a2048a35dae5d2f4b881d81689e33500f", "generation_seconds_batch": 24.95846275705844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.5738525390625, "genuineness": 4.457139015197754, "identity": 0.693152666091919, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8e9b631a4b5d43511b8c562d2ca786e42fad75da274b4949bc605afb7e0efc27.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "8ef7f2921a80b69b91499377cf0153474543c4d20c451ecce21d39d7930694fd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c54333b0b42390dab179ef46ac9badc8da77e87067d76560f1c5996c3f796402", "generation_seconds_batch": 25.216213528066874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005622804164886475, "target_z": -0.49414062356361205, "ce": 6.340320587158203, "genuineness": 4.6705241203308105, "identity": 0.4182635247707367, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/8ef7f2921a80b69b91499377cf0153474543c4d20c451ecce21d39d7930694fd.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "8fbf08c84dde929a432680843821f77e0a9af07408efb399aa6e16232fe4b897", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d648974b0a256d8e432874e110a0d5405dc45f333450fc3909e200eb84cbd524", "generation_seconds_batch": 19.810116045060568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 6.157639026641846, "genuineness": 4.419482707977295, "identity": 0.692552924156189, "hypothesis": "De deur 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_Jealousy_and_Envy/8fbf08c84dde929a432680843821f77e0a9af07408efb399aa6e16232fe4b897.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": "8fdfb40ab8ae93e5035b7cdd9824124ab81a8fed6cc30bdf74521632e1215486", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The road turns left behind the bridge.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "b30c58b91793b0b4cebc5b24ed10da87c8edfc115bfaf254e60b618bca501c96", "generation_seconds_batch": 19.14994259609375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 6.38003396987915, "genuineness": 4.419482707977295, "identity": 0.15036556124687195, "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_Jealousy_and_Envy/8fdfb40ab8ae93e5035b7cdd9824124ab81a8fed6cc30bdf74521632e1215486.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "90192c5efcc804e43449d2ff3403071bd2b0d08ad0ae47b45cd8909c72088732", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a8a6565a53766aecc145e987a658569bc202d91f6b76f0c5b22fbaec636dda8c", "generation_seconds_batch": 26.185181564069353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 6.4515180587768555, "genuineness": 4.7081804275512695, "identity": 0.26470741629600525, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/90192c5efcc804e43449d2ff3403071bd2b0d08ad0ae47b45cd8909c72088732.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "9089141acfdd4be71aeff3565524ede7ab639b173a0e0cfea59da457c145ed6f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "093935b9a54e27644dd87207076094d1dda75f73bb3b9818eceb1a3806505c08", "generation_seconds_batch": 26.603089168085717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.316492557525635, "genuineness": 4.607763767242432, "identity": 0.6002445220947266, "hypothesis": "The 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_Jealousy_and_Envy/9089141acfdd4be71aeff3565524ede7ab639b173a0e0cfea59da457c145ed6f.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "909300bed0756c63dbd6bb7e9645cac93fa722d8e277b32abcb4ee0ffe8fa064", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ba6d5d4debf69666046942e5240af64f10cf6beb57184d3caac0db7850d6ed71", "generation_seconds_batch": 18.388860790990293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 5.6532793045043945, "genuineness": 4.432034492492676, "identity": 0.6859520673751831, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/909300bed0756c63dbd6bb7e9645cac93fa722d8e277b32abcb4ee0ffe8fa064.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "911bec5a242af09ab95092f3ca8a95bf70c1668f37af92b0505344778cbb3470", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "686570053701ae303e79cc568bdfb3b00f7d1cf91ddd345ed3467a64eecc913e", "generation_seconds_batch": 25.23432087607216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 5.879645347595215, "genuineness": 4.758388519287109, "identity": 0.589754045009613, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/911bec5a242af09ab95092f3ca8a95bf70c1668f37af92b0505344778cbb3470.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "912a46d8c83a87134f178aea9d5100373491248f39ca19fea5aa5d4f6c6ab57c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "11fb3a3f9642bc999c7c008dd93430213ed8fcea1b1f52c745c16079bfaaceb8", "generation_seconds_batch": 24.22881351201795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.09409761428833, "genuineness": 4.632867813110352, "identity": 0.6600440740585327, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/912a46d8c83a87134f178aea9d5100373491248f39ca19fea5aa5d4f6c6ab57c.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "9178916c2982c5183705f882726d6de8074a46d839eedce7606c403ead359302", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c83fdc1ff14cc61aac38f761b93674a8a3f2b648b657d9c60bc79a78608395aa", "generation_seconds_batch": 24.2445097140735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007364049553871155, "target_z": -0.4980468633783156, "ce": 6.0146708488464355, "genuineness": 4.2249250411987305, "identity": 0.7123697400093079, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9178916c2982c5183705f882726d6de8074a46d839eedce7606c403ead359302.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "9183042725df3bb24e0223abf33a7b79d60d2352cfe40ad60f54b392c636110a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "57028baa84feae4c1aa157b8075965890ec0dad5fe53d4255941b1ca89b37708", "generation_seconds_batch": 18.697453832020983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 5.974957466125488, "genuineness": 4.319066047668457, "identity": 0.48956266045570374, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9183042725df3bb24e0223abf33a7b79d60d2352cfe40ad60f54b392c636110a.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "91918229208d0fc60a18641392cf86e60bb5abc7d3d531250df9c54169b063a7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c4915da7b4bf83003beb00055fab9f9d54c5d60b9bd5a94cd5c2d378f296a90f", "generation_seconds_batch": 26.678789766971022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.197352409362793, "genuineness": 4.557555198669434, "identity": 0.49132615327835083, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/91918229208d0fc60a18641392cf86e60bb5abc7d3d531250df9c54169b063a7.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "91caebb1075d5289c77aec769bcd687554b40ad7a283854c593af008499ad762", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "679ee91d1f315d1996491308b234b677f5fad810c236cd99f95f64d33857739f", "generation_seconds_batch": 25.80492114997469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.0305562019348145, "genuineness": 4.557555198669434, "identity": 0.6314868927001953, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/91caebb1075d5289c77aec769bcd687554b40ad7a283854c593af008499ad762.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "92401a59357611fb478b1831739d56460a7a62e2f19ef2a507943f049ce83a22", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8fd9e58584df893b6f87750b0f12824f922dcb6c10fb92ef9bcb1842c2ec59a0", "generation_seconds_batch": 24.25494969205465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.125868320465088, "genuineness": 4.331617832183838, "identity": 0.5833951234817505, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/92401a59357611fb478b1831739d56460a7a62e2f19ef2a507943f049ce83a22.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "92b30769d1ef46f7b4c438bf15eee39dba12c5b269fe0cb7c7453b2120fdbf5e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2a02ed61e1b57babaf0b782e6fb74897077cd19feef8b183ba50d98a285fbd09", "generation_seconds_batch": 18.240804973989725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.38797664642334, "genuineness": 4.7834930419921875, "identity": 0.30698761343955994, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/92b30769d1ef46f7b4c438bf15eee39dba12c5b269fe0cb7c7453b2120fdbf5e.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "92e0363407ae1d341f993de8e38930d7d39370490180f86cc7746d5dfda95e0d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dd6f4f2eee596d185a8cc0bb0743608b275024943f0f1b0921a65f0193d2745f", "generation_seconds_batch": 25.765472241095267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.197352409362793, "genuineness": 4.300237655639648, "identity": 0.7775300741195679, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/92e0363407ae1d341f993de8e38930d7d39370490180f86cc7746d5dfda95e0d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "938e9bf39a3a4ff84d197abf5390b3ef75ce978bd14636c0b078341cce38021a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8316b4cde637cda3aa95143246ec5b57445e5c6e04a33adf0eb95b7a3319c06a", "generation_seconds_batch": 18.87013247795403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.982900142669678, "genuineness": 4.532451152801514, "identity": 0.6362186074256897, "hypothesis": "De deur 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_Jealousy_and_Envy/938e9bf39a3a4ff84d197abf5390b3ef75ce978bd14636c0b078341cce38021a.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": "9392020ca45abbe8a4276b109258af8afec63ae3fb1080e1902096c6183cb9ab", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8ab2d7da136f1ba4ec64b2f57bf8c1249f45222aeaf741ce402aa3bc5cf98f8b", "generation_seconds_batch": 25.846327931038104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 5.673136234283447, "genuineness": 4.344170093536377, "identity": 0.6158684492111206, "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_Jealousy_and_Envy/9392020ca45abbe8a4276b109258af8afec63ae3fb1080e1902096c6183cb9ab.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "93fe84e43633974988a161cd4d8bcb7950b69aac95c0b64428b70cfc88aa4518", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d3dff0e504c373be93bbfd32bbce0bd8602b73ff0d94c75688085e56bc7a4add", "generation_seconds_batch": 18.473344001104124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.704906940460205, "genuineness": 4.444586753845215, "identity": 0.7316431999206543, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/93fe84e43633974988a161cd4d8bcb7950b69aac95c0b64428b70cfc88aa4518.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": "941e756a691731600d6b9b5c655235a42991ae372ea76caeb097f609533308ea", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Your message arrived after I had left.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25f078554cf13e2e216b91f3de80143cf8222674ef64abe6d0f21c8e78b22b8b", "generation_seconds_batch": 25.13933424698189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 6.395919322967529, "genuineness": 4.406930446624756, "identity": 0.39603865146636963, "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_Jealousy_and_Envy/941e756a691731600d6b9b5c655235a42991ae372ea76caeb097f609533308ea.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "942cd23ce6581c96ee1f29929bef73b4c7c97fa6bedb7985ef13e184023193b7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "405e18863f81db115f47c563d86289d821c5dde894cf7e1fb3b24e37802d3b17", "generation_seconds_batch": 26.17577479290776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.839932441711426, "genuineness": 4.65797233581543, "identity": 0.7715280652046204, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/942cd23ce6581c96ee1f29929bef73b4c7c97fa6bedb7985ef13e184023193b7.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "9466b47e6a5247483371de6a619297f2fb40fdc50bba6ad35c7a0636b2e24c27", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e5334ee24a4b31e76ca1945213fbc01354858efd6cca86d874bc20dd65e10687", "generation_seconds_batch": 18.951766718993895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.062326908111572, "genuineness": 4.011539936065674, "identity": 0.6894712448120117, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9466b47e6a5247483371de6a619297f2fb40fdc50bba6ad35c7a0636b2e24c27.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "950cefe349f5b596eafa8a3b8c962138205973267db329484d408134315a0b4f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fbe623e8cfc8e99a3ececc779e853fa75c5bffcd4f65cc7393b73d04731a69d9", "generation_seconds_batch": 18.41673662106041, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.8157316446304321, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/950cefe349f5b596eafa8a3b8c962138205973267db329484d408134315a0b4f.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "956e6732b41ea19ed960d3830e85d47d51b104a41954dfa3b81ff65aab7bbe76", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "376d9667b2e545701b45293c54e1d5396ec77fa3c3ba1851639a87f8226154d8", "generation_seconds_batch": 24.366160852950998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.847874641418457, "genuineness": 4.118232727050781, "identity": 0.6744407415390015, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/956e6732b41ea19ed960d3830e85d47d51b104a41954dfa3b81ff65aab7bbe76.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "95dcf22ef1809bbca19d203e8e90337fc74b6b78e43eba2fdd5583f203a67d32", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0794a4c478f478bea60cbd176980a18aa600862197cc8c1699d8f37ab0828cde", "generation_seconds_batch": 25.664753176039085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.300607204437256, "genuineness": 4.1998209953308105, "identity": 0.41156214475631714, "hypothesis": "The 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_Jealousy_and_Envy/95dcf22ef1809bbca19d203e8e90337fc74b6b78e43eba2fdd5583f203a67d32.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "9613a8ac39bff12cddc08305ace8889a3b07adae15f4b7e232a89c3bd362d9f3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b726ca54474b1798bd8999c580d546a58c23eeb63c4fdfb4f931bc2e5d6c51cf", "generation_seconds_batch": 25.25249009404797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.23706579208374, "genuineness": 3.9927117824554443, "identity": 0.4512040615081787, "hypothesis": "The 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_Jealousy_and_Envy/9613a8ac39bff12cddc08305ace8889a3b07adae15f4b7e232a89c3bd362d9f3.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "96fec6a89f972cec026e43b5f2186260a0786a7e32eb6fee7af582f3a348970c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d8284995a3f4a96f5498c06ff64a7496a1789ddaa5eb99904eb77e7bc2b32884", "generation_seconds_batch": 18.99186313606333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032684698700904846, "target_z": -0.40820311363947703, "ce": 5.855817794799805, "genuineness": 4.6956281661987305, "identity": 0.7433719635009766, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/96fec6a89f972cec026e43b5f2186260a0786a7e32eb6fee7af582f3a348970c.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": "970fb7e1912c65397b1346c5bfe11d3bbe6be5febb4384aeecae7ae0a0c233af", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I wrote the number on the envelope.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51a7dcd78b2bff21160fc4006c08f7e10306d027f92ee056fe743e63695c02d5", "generation_seconds_batch": 25.67459701898042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.268836498260498, "genuineness": 4.545003414154053, "identity": 0.21408572793006897, "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_Jealousy_and_Envy/970fb7e1912c65397b1346c5bfe11d3bbe6be5febb4384aeecae7ae0a0c233af.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": "97239dca3397905f0ca34a957132b170674fd3c2ad593af9bc18d7593fe106cc", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "92ce92eaa4b197339e7e9b91fd8d40577297ea95b3e01e25dc2401769d23e5cd", "generation_seconds_batch": 20.73326841101516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.927301406860352, "genuineness": 4.268857479095459, "identity": 0.5339199304580688, "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_Jealousy_and_Envy/97239dca3397905f0ca34a957132b170674fd3c2ad593af9bc18d7593fe106cc.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "973991dbafce7ffc3525916f09b05546e7048064bfafad87d3ed3dd76eb4d406", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f2182e19778830164fc383e2f877a8cee7cf6d5cbdd1a259d9612243459e5f20", "generation_seconds_batch": 26.610011057928205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 6.09409761428833, "genuineness": 4.268857479095459, "identity": 0.3644103407859802, "hypothesis": "The 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_Jealousy_and_Envy/973991dbafce7ffc3525916f09b05546e7048064bfafad87d3ed3dd76eb4d406.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "975ef7bbd1f9346119abde2f9cd64c5493887ffcc630338197012ebb7d61df00", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1dedf16e03760723e38b70503689875b8269931ada6f9a8878c5d62f9d3d82ac", "generation_seconds_batch": 27.52519336901605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 5.974957466125488, "genuineness": 4.570107460021973, "identity": 0.47569894790649414, "hypothesis": "De deur 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_Jealousy_and_Envy/975ef7bbd1f9346119abde2f9cd64c5493887ffcc630338197012ebb7d61df00.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "97a697726da98ad09aca502d6f8771c4047f4fc4d8c34abbeb3d170381dcece5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d5853c6b008c98f95fe50faefb578850c7bd39b36930453ad0a188e036e7d4e2", "generation_seconds_batch": 26.163546808063984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.070269584655762, "genuineness": 4.582659721374512, "identity": 0.728881299495697, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/97a697726da98ad09aca502d6f8771c4047f4fc4d8c34abbeb3d170381dcece5.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "97bf4c0374d45675f9ecdfe9501c2436b61ae9ffdf51ff42d232da23b8ebcb6e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fc65af82d6856af7a155bcc84de337cd62cb5c6fae82100a02e69c309ba5a8a6", "generation_seconds_batch": 25.162855291971937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 5.990842819213867, "genuineness": 4.218649387359619, "identity": 0.6716782450675964, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/97bf4c0374d45675f9ecdfe9501c2436b61ae9ffdf51ff42d232da23b8ebcb6e.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "97d01a204c307b8791ecd7d0257f96f484ffa3fc62610b05d2181276626d2cf0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "41c720f9d0b58ed006adee9a64dd5664fae11f3a22a2383dabcfdbeb120deb2c", "generation_seconds_batch": 25.06428135605529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.038498878479004, "genuineness": 4.7081804275512695, "identity": 0.68113112449646, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/97d01a204c307b8791ecd7d0257f96f484ffa3fc62610b05d2181276626d2cf0.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "9805420e1f871e0f9788270dd54976f16e7e1c08d22ae5ad6ecc6a44d24a7fc1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4b1e93466703ad24bbf3a03317a3592bd8553a545290df34c5b7b9739a1da6f8", "generation_seconds_batch": 23.950500419014134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.9431867599487305, "genuineness": 4.65797233581543, "identity": 0.6284924745559692, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9805420e1f871e0f9788270dd54976f16e7e1c08d22ae5ad6ecc6a44d24a7fc1.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "981a129455bda58c5709cfad1fcfd22de98de007efe05fb8f1318270d7bfcf1c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9d05722fdcc440a4d87d202ac01cd834fc57a4aab405df37b91eefdece4c0319", "generation_seconds_batch": 18.080471908091567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.982900142669678, "genuineness": 4.65797233581543, "identity": 0.6740596294403076, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/981a129455bda58c5709cfad1fcfd22de98de007efe05fb8f1318270d7bfcf1c.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": "98923fc61ea49d6cfe97bf6d12e8827ab5baef1f4d6c30b0405071af831a812a", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Your message arrived after I had left.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "4b3f87b5334e154bf37127d41cceef07a4c6f479df5fb09b7ee960a9dd5bd332", "generation_seconds_batch": 18.34335177799221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03355531394481659, "target_z": -0.40625001044645787, "ce": 6.308549880981445, "genuineness": 4.394378662109375, "identity": 0.28419846296310425, "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_Jealousy_and_Envy/98923fc61ea49d6cfe97bf6d12e8827ab5baef1f4d6c30b0405071af831a812a.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "98d7377f82c66c889c21cccd72aa878341ece1413ea473270c866dfa860e8fa5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "91727fdf41cc40222bfb895f56344eaa76d3834abd81ef3d60b5009de47ecc1a", "generation_seconds_batch": 26.610086822067387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.006728172302246, "genuineness": 4.306513786315918, "identity": 0.6831265687942505, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/98d7377f82c66c889c21cccd72aa878341ece1413ea473270c866dfa860e8fa5.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "98dc37e832d07d3b01431e61e032d2f2992aa91d8521e207615706616244e020", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ab2ff05eec4c08072c20976b97669f3273c6e0ef6a70501d7f572528fdb9fcb5", "generation_seconds_batch": 17.64128833496943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 5.982900142669678, "genuineness": 4.20609712600708, "identity": 0.5874350070953369, "hypothesis": "De deur 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_Jealousy_and_Envy/98dc37e832d07d3b01431e61e032d2f2992aa91d8521e207615706616244e020.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "98df3ff440d34ef0f8d7b02a03793e54b4a9e24638f0c87c9e94eeb0823fdd03", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d4474f9f229de116de19247a9e1f088983d26d22392251c98bfd4d21e3732c77", "generation_seconds_batch": 26.05523832293693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 5.289902210235596, "genuineness": 4.507347106933594, "identity": 0.6631401181221008, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que", "wer": 0.11764705882352941, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/98df3ff440d34ef0f8d7b02a03793e54b4a9e24638f0c87c9e94eeb0823fdd03.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "98ede883f1ca704b39c2575ef86343259a60975b1d3715422631a4771b43e4d0", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c27ff5a3a9f97ec6132b9478d3bd42a820368ba84f256ef64dd62d0a3e310f2d", "generation_seconds_batch": 20.110675685922615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.38797664642334, "genuineness": 4.595211505889893, "identity": 0.3979513645172119, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/98ede883f1ca704b39c2575ef86343259a60975b1d3715422631a4771b43e4d0.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "992ce1a1110fe965ef68537250d7fa9bd2ef6ff1450550f94d2d493916d64c1a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bd273fbfc92c227d83f6dd53446add2eee7fb086df7333d79da2af60767c6fd9", "generation_seconds_batch": 23.934082203079015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 6.2767791748046875, "genuineness": 4.482243061065674, "identity": 0.4323793053627014, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/992ce1a1110fe965ef68537250d7fa9bd2ef6ff1450550f94d2d493916d64c1a.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "995d8a8f9cd364dd18356ebb56bf8693f56088ca3300f5e8a06a8088f93779a6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "47f6b5768aed5766437668fa4de414310de85741df5e485a8afdc6e6e9ad4344", "generation_seconds_batch": 28.09126195695717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.696964263916016, "genuineness": 4.645420074462891, "identity": 0.6449761390686035, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/995d8a8f9cd364dd18356ebb56bf8693f56088ca3300f5e8a06a8088f93779a6.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "9986b93b81407df204978c6adcb27d9ac79d5515c659ddc1ca8311fcb74e09e0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ec72b10f26bbb77ff2acceecd4740db20bf90566d89edd1a5747c09420311f89", "generation_seconds_batch": 24.093321786029264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.998785495758057, "genuineness": 4.796044826507568, "identity": 0.601753830909729, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9986b93b81407df204978c6adcb27d9ac79d5515c659ddc1ca8311fcb74e09e0.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 129, "seconds_generated": 10.32, "mp3_sha256": "470df452837f495734d2ddd385406de0154afaef7b46f7b0e542cdbd5e0c514e", "generation_seconds_batch": 17.941024234052747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03355531394481659, "target_z": -0.40625001044645787, "ce": 6.356205940246582, "genuineness": 4.632867813110352, "identity": 0.4416820704936981, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "99e977992e73832e795a08490d7b0eb0d67847c8803fe80d6a3ea3866eb8cf3b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ea2e75ea246cbb8401009a0098afb9b16df7dada7b1f8a8b24e1c0a6389f6012", "generation_seconds_batch": 23.604830770986155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.268836498260498, "genuineness": 4.394378662109375, "identity": 0.6834378838539124, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/99e977992e73832e795a08490d7b0eb0d67847c8803fe80d6a3ea3866eb8cf3b.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "99fcc2000434fe4d7ab10fd15cba0a3e4af76c5817afb5167ef9027774a6ff84", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d1cfdcf9889e7ce1e9f121ed82f7cce7f6e605a4883f2b5e4b05faa6664c4ba6", "generation_seconds_batch": 19.582827068050392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 5.8875885009765625, "genuineness": 4.394378662109375, "identity": 0.6146597862243652, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/99fcc2000434fe4d7ab10fd15cba0a3e4af76c5817afb5167ef9027774a6ff84.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "9a5f0606431e2e0a9e4d698be3ef0c6b4fe549b640cc98b109ae84f769ccd32c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5f43479d1bca5a7ca07da85d193e13ff2e0403848a5c712a5b33862877bd1bf6", "generation_seconds_batch": 17.170765534974635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.038498878479004, "genuineness": 4.193545341491699, "identity": 0.6887049674987793, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9a5f0606431e2e0a9e4d698be3ef0c6b4fe549b640cc98b109ae84f769ccd32c.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "9a7ce37f47f3fca4f607269937718661ad304a595be3fde9610ecdf2eec00079", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a3636aed90b98ed3f4a07a1aab01cd36fc76f1b318d2ee3354fdb91f2a7ef822", "generation_seconds_batch": 26.05523832293693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 5.49045467376709, "genuineness": 4.645420074462891, "identity": 0.7973647713661194, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9a7ce37f47f3fca4f607269937718661ad304a595be3fde9610ecdf2eec00079.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "9b14e5a5a8d455f34c8f96361d020288144916a13c02add9e8ea78aec44e3cb0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b0d01d3eebe86dcfa32365e19ccd64e911340a01c295b491570482cf7d024fc4", "generation_seconds_batch": 24.58417611196637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 5.935244083404541, "genuineness": 4.632867813110352, "identity": 0.6191025376319885, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9b14e5a5a8d455f34c8f96361d020288144916a13c02add9e8ea78aec44e3cb0.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "9bb308d900ff07c62bae0ee6d0a32aef5286028f90e0a4e2a7742b49f6510217", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "572383582be3981a15951d310c8b8efe6ad1266baaf957b69de459bfc3873f59", "generation_seconds_batch": 28.800194176961668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.229123115539551, "genuineness": 4.758388519287109, "identity": 0.6327756643295288, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9bb308d900ff07c62bae0ee6d0a32aef5286028f90e0a4e2a7742b49f6510217.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "9be22a7cbe2f142e867158a5e55fa2a394ba2914eb75fccc91745fa9a752d890", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "58e4d025653ebcb54cee65f12737525b9905f640c0add9d2740cc1cee9b997d7", "generation_seconds_batch": 25.23288531997241, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 6.308549880981445, "genuineness": 4.381826400756836, "identity": 0.2992452085018158, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9be22a7cbe2f142e867158a5e55fa2a394ba2914eb75fccc91745fa9a752d890.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "cb5c4759bc0378200f1f6ea6b988f447e73906abe034c4d5f1c86bba003178e2", "generation_seconds_batch": 19.787600410054438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.284721851348877, "genuineness": 4.444586753845215, "identity": 0.7105313539505005, "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_Jealousy_and_Envy/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "9c48d67ca66b3186bf327908fc66be3e61b3e84d20a331ab59fb34b57c004633", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f9992213135646a73c0fefafd391021bb4d230765477c5b2f4cb0aeeefbd8a45", "generation_seconds_batch": 25.04970232094638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.157639026641846, "genuineness": 4.337893962860107, "identity": 0.5706669092178345, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9c48d67ca66b3186bf327908fc66be3e61b3e84d20a331ab59fb34b57c004633.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "3e4a16f9e0b51b47f1cf8a9c3ade0444ead3a8fa40ea3ddb46c28b9f21240bf7", "generation_seconds_batch": 18.624153074924834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01694093644618988, "target_z": -0.5195312659308483, "ce": 6.197352409362793, "genuineness": 4.287685871124268, "identity": 0.3452528119087219, "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_Jealousy_and_Envy/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "9ce22a02ba1f2fcc989f864574be118918cdad8e17a8d3ad24c1cedaed02ec71", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c9c9fefd859e8d014e79228ce4d7a6ebb10da98704fec6ec726ad96c8c1c73e6", "generation_seconds_batch": 25.593534043990076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.475345611572266, "genuineness": 4.432034492492676, "identity": 0.6444939374923706, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9ce22a02ba1f2fcc989f864574be118918cdad8e17a8d3ad24c1cedaed02ec71.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "9ce4f94b32a179212ed7bb376c815421c7d66bc25df0e7a0596873ea0fe9349b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6a4930262fc47bdf9d8c5b55fe102683cd7a8ffc9bb7a3f58a6d9222078a8e40", "generation_seconds_batch": 17.78251366096083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.205295085906982, "genuineness": 4.507347106933594, "identity": 0.22080115973949432, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9ce4f94b32a179212ed7bb376c815421c7d66bc25df0e7a0596873ea0fe9349b.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "9d373934703b143d3f36c49bafbe53d7640f8fcdabef4e1e8d736e1cf0d11c59", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "94fcb26ca885a43211c22a9084e9755469a33ee5523ad5e63810d97183330787", "generation_seconds_batch": 18.364206062979065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.316492557525635, "genuineness": 4.325342178344727, "identity": 0.4111490547657013, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9d373934703b143d3f36c49bafbe53d7640f8fcdabef4e1e8d736e1cf0d11c59.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": "9d3f0680c0b2e168788d2e8f3f4366d40175857bb19739a205554dcda441b231", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "8e5d3ae5f3e5f2e5884a501baccb9acb005e4375b17923af22bf77769d1ec67c", "generation_seconds_batch": 18.767719274037518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.125868320465088, "genuineness": 4.570107460021973, "identity": 0.8018808364868164, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster, nimm sie ihm mit, wenn du gehst.", "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_Jealousy_and_Envy/9d3f0680c0b2e168788d2e8f3f4366d40175857bb19739a205554dcda441b231.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "9d4bfea6da650badd996b9f7cd3f52d20c2f94812e29408d5ae1409b7ed0f15f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fd0bf0014770e8a7f537a7524b744880eaa64fdfa57d36e0fe2e243f6e8c8641", "generation_seconds_batch": 25.983740528929047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 5.919358730316162, "genuineness": 4.356721878051758, "identity": 0.6196810603141785, "hypothesis": "De deur 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_Jealousy_and_Envy/9d4bfea6da650badd996b9f7cd3f52d20c2f94812e29408d5ae1409b7ed0f15f.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "9ddff9dc0d3cb761a4ff16d6e605c1443425236a9347500569d33429ce2478b5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4039e2d65e3b0f2ddabf9526610f0ab21ca836783eb31d5501bbc2c639bc6e1c", "generation_seconds_batch": 23.66483902791515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03007282316684723, "target_z": -0.41406249007586504, "ce": 6.070269584655762, "genuineness": 4.425758361816406, "identity": 0.2640652060508728, "hypothesis": "The 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_Jealousy_and_Envy/9ddff9dc0d3cb761a4ff16d6e605c1443425236a9347500569d33429ce2478b5.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "9de99fdd491f44d02bcd02d03a944b98ff2ebe945ce9cdda2849b442f06df207", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2366ee2b875c5627013fe1426910a00f9d15b69f8cd79e505339ae65b0a6cbda", "generation_seconds_batch": 18.87741148704663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.006728172302246, "genuineness": 4.281409740447998, "identity": 0.6375782489776611, "hypothesis": "De deur 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_Jealousy_and_Envy/9de99fdd491f44d02bcd02d03a944b98ff2ebe945ce9cdda2849b442f06df207.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "9df82ac84524df80badf33929c296aa138895615e23f18cbb87c5e1c1df5468b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f85dbea1ac23455310a79c940b2d56c83751a4de201921edb106078fd313616e", "generation_seconds_batch": 25.554383600014262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.427689552307129, "genuineness": 4.6203155517578125, "identity": 0.4181421995162964, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9df82ac84524df80badf33929c296aa138895615e23f18cbb87c5e1c1df5468b.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "9e002d30889a5d0357ef15f6a05fefc8fd0b24a0fde12161109378130a07a40d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "559b0593e418eedbbdf29a59eaa3d4af888a72162ca56b6c039d31a4e193799e", "generation_seconds_batch": 25.854997836984694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.173524379730225, "genuineness": 4.6203155517578125, "identity": 0.7706185579299927, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9e002d30889a5d0357ef15f6a05fefc8fd0b24a0fde12161109378130a07a40d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "9e1a3dd59b41b28cc836ce6797262a221de23b096698efea7e3fecddba88ce8b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "182a96bfbd5d954ced87c878d447e9233fdfbb6c8be78f479182a780d41937e7", "generation_seconds_batch": 24.376648970064707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 5.728734970092773, "genuineness": 4.13078498840332, "identity": 0.4638107120990753, "hypothesis": "De deur 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_Jealousy_and_Envy/9e1a3dd59b41b28cc836ce6797262a221de23b096698efea7e3fecddba88ce8b.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "9e1ac5931b0ecd61029a6e08504df6abb61aea5332e995f0093c73e5294717f9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b9a8f21554ec8abbda9cd19e4ca2925b86949c9b46a331367cb83f50860c5cca", "generation_seconds_batch": 23.178744758013636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.855817794799805, "genuineness": 4.080576419830322, "identity": 0.642810583114624, "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_Jealousy_and_Envy/9e1ac5931b0ecd61029a6e08504df6abb61aea5332e995f0093c73e5294717f9.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "9e8dce6b99223794f0c4db86014fbc8ec96b0f976549362918c7279a2acff491", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "acab629f36ce6b87e04f9420d37f3f43795073947c62366ec2758e4ab87b6f10", "generation_seconds_batch": 25.702681162045337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 6.213237762451172, "genuineness": 4.545003414154053, "identity": 0.2543225586414337, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9e8dce6b99223794f0c4db86014fbc8ec96b0f976549362918c7279a2acff491.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "9ea5354c2fa05f0bb84a55839c1e09e8fa15956b985c1f264480dbe669290a65", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2bbe169a694421eb44167d6b638ef4baf4eec71082c60c6a68240d835067e87f", "generation_seconds_batch": 24.859505741042085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.95112943649292, "genuineness": 4.306513786315918, "identity": 0.6504005193710327, "hypothesis": "De deur 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_Jealousy_and_Envy/9ea5354c2fa05f0bb84a55839c1e09e8fa15956b985c1f264480dbe669290a65.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": "9f8effe7d79e17ffe4c45b186f2de191c0772bb6fa74b1a9d8fc10de0a860826", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79d0004860815f3dc08267190ce45112cd17a7f2c9c3f4b956d0b59d0b535d7e", "generation_seconds_batch": 24.686428055050783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.49045467376709, "genuineness": 4.356721878051758, "identity": 0.29986250400543213, "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_Jealousy_and_Envy/9f8effe7d79e17ffe4c45b186f2de191c0772bb6fa74b1a9d8fc10de0a860826.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "9f917dbe132b77b79ed56ef488141719102fa432fcdcd0f422238376a58173a3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7d30f53dfac8070478ebde7cca6830921cd2f7411705b7635d9ecd30028c489c", "generation_seconds_batch": 24.9499953960767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.149696350097656, "genuineness": 4.149612903594971, "identity": 0.38300958275794983, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9f917dbe132b77b79ed56ef488141719102fa432fcdcd0f422238376a58173a3.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "9f9cce56889cd3f823fbafe4b57ca1d423b16761598fb11615674e9ed6d8acbf", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f328d8c66b744ae9ff198f8ced9a3fd12ce2e85962cfafb59342e3bebe9ede2c", "generation_seconds_batch": 25.641709838993847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.816103935241699, "genuineness": 4.344170093536377, "identity": 0.5336064100265503, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/9f9cce56889cd3f823fbafe4b57ca1d423b16761598fb11615674e9ed6d8acbf.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "a02737236ddf3b8983c32dbccc4828eaadbea2240540ac35b0d61417dd80bca9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7a76e6a400576499e535c731523c1ae797415a321356ee709f090bd741879111", "generation_seconds_batch": 25.40307593799662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.070269584655762, "genuineness": 4.570107460021973, "identity": 0.7902787923812866, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a02737236ddf3b8983c32dbccc4828eaadbea2240540ac35b0d61417dd80bca9.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "a03e4ca0052e2b0d9b4a40d081bd5ad4ba4f10a11ed2f7b1334fa8ba512c9579", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee04827540566e681b9c7012356d57d4f7ddb67cc8f035f4c70a3eace1c2c797", "generation_seconds_batch": 22.078744038939476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 5.589737892150879, "genuineness": 4.557555198669434, "identity": 0.6952588558197021, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que.", "wer": 0.11764705882352941, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a03e4ca0052e2b0d9b4a40d081bd5ad4ba4f10a11ed2f7b1334fa8ba512c9579.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": "a06b006e6790a867cddc74af56af247fe711ac3a605164555c5d4b86d98e0932", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Escribí el número en el sobre.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "e3942a1f75274d3d4fd482a5676b8a5d43e4e5f910519db8d5a8a0c7ad9e3767", "generation_seconds_batch": 18.995592257007957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02216467261314392, "target_z": -0.5312499853749589, "ce": 5.9431867599487305, "genuineness": 4.595211505889893, "identity": 0.5846982002258301, "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_Jealousy_and_Envy/a06b006e6790a867cddc74af56af247fe711ac3a605164555c5d4b86d98e0932.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "a13afaad96a003326bfbf463fef177f519d9afb8f9fbb645363538a459deb443", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b091da39281f1ecb8e1b606d4a74be824cef4a4cb3b19edf5c74fc6b7ef1003", "generation_seconds_batch": 18.202773513970897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 6.062326908111572, "genuineness": 4.507347106933594, "identity": 0.31367284059524536, "hypothesis": "The 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_Jealousy_and_Envy/a13afaad96a003326bfbf463fef177f519d9afb8f9fbb645363538a459deb443.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "a165492d243a40bd4f8776c43d34361113cb31935368197905f978f7839b4215", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "29d5e6a9c846a9f9f126b08805d1052341244ffca800a608fc6f2dada4b007d8", "generation_seconds_batch": 26.719967841054313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.062326908111572, "genuineness": 4.319066047668457, "identity": 0.8027819395065308, "hypothesis": "De deur 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_Jealousy_and_Envy/a165492d243a40bd4f8776c43d34361113cb31935368197905f978f7839b4215.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "a1a369caf2a4d4582e761e45ac4bcb8547c070393af86dc6aa3e233dc538dd13", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3593664a4c294d96fe9283270a2bbdaf0737f4cbc2eecff6acb88be0de46a043", "generation_seconds_batch": 33.43075503304135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 5.657250881195068, "genuineness": 4.444586753845215, "identity": 0.6956229209899902, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a1a369caf2a4d4582e761e45ac4bcb8547c070393af86dc6aa3e233dc538dd13.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "a1b34c8187c8fab6c823dfe06fbaf2f951cd111acb3b0e593d579bc67b7cb72c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f4a0b4be891f975d899db58692bf2516cd961a439e4fff50f55854b3c794567d", "generation_seconds_batch": 24.709344442933798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.4825119972229, "genuineness": 4.381826400756836, "identity": 0.7340009212493896, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a1b34c8187c8fab6c823dfe06fbaf2f951cd111acb3b0e593d579bc67b7cb72c.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": "a23b6644a203090400482652af219717b3ae8cea46769aabe5ecc4fb51b13994", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bf1a79385ba26f12d2afd2db6a23b4f20a1796492bb1a20ec55b9b45688c0df3", "generation_seconds_batch": 24.607758957892656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.903473377227783, "genuineness": 4.607763767242432, "identity": 0.6576616764068604, "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_Jealousy_and_Envy/a23b6644a203090400482652af219717b3ae8cea46769aabe5ecc4fb51b13994.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "a27e9bc48ee048c95e1110c0526d92f0df07ad5cafb9e5a0f0d713ad2be94afa", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea58a18671be4ec3ed41232e60585162f196992e6b945b4ddb95c83f7d5b9b81", "generation_seconds_batch": 25.493456746917218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.070269584655762, "genuineness": 4.193545341491699, "identity": 0.26989057660102844, "hypothesis": "The 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_Jealousy_and_Envy/a27e9bc48ee048c95e1110c0526d92f0df07ad5cafb9e5a0f0d713ad2be94afa.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "a281c56e46bc710e155299470ca5ab8408ba7dac187ab5e1e898389cd3ad359c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "07debb324094da366ea5e4b59860edf1b04727ab78098bf86b8d326d303caa52", "generation_seconds_batch": 29.463313655927777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 5.839932441711426, "genuineness": 4.344170093536377, "identity": 0.6682907342910767, "hypothesis": "De deur 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_Jealousy_and_Envy/a281c56e46bc710e155299470ca5ab8408ba7dac187ab5e1e898389cd3ad359c.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "a2db95e4016e723fc4e06686853456a99023cd64bd75fd195e8c9a2702a88699", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d6e43f9e933e85f0b5548cfa2041a01792f6250a3bdbd5fd9ce3e56587d16082", "generation_seconds_batch": 26.024463378009386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.078212261199951, "genuineness": 4.444586753845215, "identity": 0.7735347747802734, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a2db95e4016e723fc4e06686853456a99023cd64bd75fd195e8c9a2702a88699.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "a2e50b551fc74730d6c17bdbc178665e3fb39fbae776d93a70d7a663cbcb414e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7bda8aad11964d4ff18e439a637e0619651b4706d768de45f44d6d91ead97bd8", "generation_seconds_batch": 23.453187841922045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.0305562019348145, "genuineness": 4.331617832183838, "identity": 0.6889148950576782, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a2e50b551fc74730d6c17bdbc178665e3fb39fbae776d93a70d7a663cbcb414e.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "a330087950dc0c51d55f973b7474dceca36d37427ab5741643f1711012917f19", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "110029f23e52ea7fbe266e5e6ee0e7987c8570c2deecf117d872ebfc7a64ba44", "generation_seconds_batch": 26.610011057928205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.157639026641846, "genuineness": 4.268857479095459, "identity": 0.2967716455459595, "hypothesis": "The 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_Jealousy_and_Envy/a330087950dc0c51d55f973b7474dceca36d37427ab5741643f1711012917f19.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "a3400e9618fdba85963d6a6c4a632a224d9a7b30ea793b7e428645055e1ac3b4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6a3f72087d6e91123f79fa10e16cb9d5361e64468c7969f4856fe58aa685ce41", "generation_seconds_batch": 24.588115821010433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 5.895530700683594, "genuineness": 4.909013748168945, "identity": 0.6972135305404663, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a3400e9618fdba85963d6a6c4a632a224d9a7b30ea793b7e428645055e1ac3b4.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": "a589ec06bd8a2d93605d3c8b9d270798fa10e3931bb5f717a5a9c6755941ff15", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "0a5b29b0265632e641331292cfba48f7b3b221363b21c316f0112455e5bcd392", "generation_seconds_batch": 19.034643503953703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005622804164886475, "target_z": -0.49414062356361205, "ce": 5.7684478759765625, "genuineness": 4.532451152801514, "identity": 0.6619290113449097, "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_Jealousy_and_Envy/a589ec06bd8a2d93605d3c8b9d270798fa10e3931bb5f717a5a9c6755941ff15.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "a5ff91edd517de7b4da56bf2346ae8d75511c9a8f18e71f0e556397f56f25880", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 130, "seconds_generated": 10.4, "mp3_sha256": "200ddc8a5bc12a27892b72cfaad3eda646515ca119cffb288d7c3fde2a1b9c07", "generation_seconds_batch": 30.53810681705363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.454712867736816, "genuineness": 4.231201171875, "identity": 0.606824517250061, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.20000000000000107, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a5ff91edd517de7b4da56bf2346ae8d75511c9a8f18e71f0e556397f56f25880.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "a63209bef0cad0d415bebceb5fecc738ad08f57171ae6b23cb37b77e3c55aab8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "908fc8e5a6bc7160699f9db719d17a204103efc78c2138c7f580d74e8b5ee471", "generation_seconds_batch": 25.8323218600126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 6.0305562019348145, "genuineness": 4.369274139404297, "identity": 0.5766732692718506, "hypothesis": "De deur 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_Jealousy_and_Envy/a63209bef0cad0d415bebceb5fecc738ad08f57171ae6b23cb37b77e3c55aab8.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "a63b8723c7b71d0e4e2c1b74e3c7234aacf2f60460194a83b7b322e601200751", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5e31a6491b9e426355ee2f47a311073adf417a6fed1c37f832e4e975ffaba064", "generation_seconds_batch": 25.733686294057406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.062326908111572, "genuineness": 4.532451152801514, "identity": 0.708124041557312, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a63b8723c7b71d0e4e2c1b74e3c7234aacf2f60460194a83b7b322e601200751.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "a64e79141b6d7a3c91126a6136d9dc6b03f64f77ab86be83426dc09a500a5d25", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b0eb1c34d25681dbf18a4dbc8672a1f9505b18333bec7463cb2cedd45137c86f", "generation_seconds_batch": 28.09126195695717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 5.911416053771973, "genuineness": 4.7081804275512695, "identity": 0.7278972268104553, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a64e79141b6d7a3c91126a6136d9dc6b03f64f77ab86be83426dc09a500a5d25.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "a659fd4eeea641c160fa86662813c407bbd1b0463c4f137dbb5bfd60840657f0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8af0149712020d74f107a28723f12b581356f072bc619ab3ce012c8a61affef0", "generation_seconds_batch": 21.885866347001866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.982900142669678, "genuineness": 4.482243061065674, "identity": 0.5946370959281921, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a659fd4eeea641c160fa86662813c407bbd1b0463c4f137dbb5bfd60840657f0.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "a683c36506e1b88906c7cdf00ba1c905fb8a028a1f7c7efe521c46f73edcb6ad", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2617369ac4fd9e0c504c1b83c2b212191bdf940e6a8c6fd8d83edb81480e3389", "generation_seconds_batch": 19.582827068050392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 5.982900142669678, "genuineness": 4.632867813110352, "identity": 0.64005047082901, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a683c36506e1b88906c7cdf00ba1c905fb8a028a1f7c7efe521c46f73edcb6ad.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "a6a56ecfcff6892335ba59771dca1c6ef0e9b41279b0e435909a0e5139604be4", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "814b3e408ba4b5ce1d9148dd06825ad535abb3ee70f4328ada1f3290ab30567a", "generation_seconds_batch": 19.29978649294935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.23706579208374, "genuineness": 4.6956281661987305, "identity": 0.7723739743232727, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a6a56ecfcff6892335ba59771dca1c6ef0e9b41279b0e435909a0e5139604be4.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "a6ad20be8eb6c8f6923609844071dc528406ebdf7a06b0051987634d61ca53ad", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6c90221494ca65cb2853ccbde9adc6a21ea7825f1a50d7ca4601e4ea278ba6b9", "generation_seconds_batch": 25.441644023987465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 5.998785495758057, "genuineness": 4.632867813110352, "identity": 0.6705201864242554, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a6ad20be8eb6c8f6923609844071dc528406ebdf7a06b0051987634d61ca53ad.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "a733631977f8c10c90a6875757ab583485ccecdd23953afc22b9429635231167", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cef4f9b9eaaa2288500524e36a26c2e8635117df3e6924be437f6d2170b2e6a4", "generation_seconds_batch": 19.2782993450528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.117925643920898, "genuineness": 4.293961524963379, "identity": 0.6408827304840088, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a733631977f8c10c90a6875757ab583485ccecdd23953afc22b9429635231167.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "a76ba128fd8c674c19e14fee7bf089de7ddfe1ece9bed503233be09962da3403", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f9e1b1dfd966cef39f9f490cb94dd1d25210ac90d368cce24a29a04c55845b4a", "generation_seconds_batch": 22.183799137943424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.054384231567383, "genuineness": 4.7081804275512695, "identity": 0.6910325288772583, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a76ba128fd8c674c19e14fee7bf089de7ddfe1ece9bed503233be09962da3403.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "a85a67dafdd1d4a2fa6154d4c58fa9f7a8ed5465739a98025cfc849744afaa2f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a6d4b1aa2c4dfd1dd0610d8b14ac6b56fabb125ba9c7db539044f9c247608f5a", "generation_seconds_batch": 25.488854003022425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 5.824047088623047, "genuineness": 4.394378662109375, "identity": 0.7025987505912781, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a85a67dafdd1d4a2fa6154d4c58fa9f7a8ed5465739a98025cfc849744afaa2f.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "a86fe9611be218c9215f2c81a51976a5994eae30fab949273debd441ae7cbc2a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f469b6932ab708f050f6e34af9b6042299953b5d6e63659204b0b006a4cb7200", "generation_seconds_batch": 27.25079905707389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.046441555023193, "genuineness": 4.432034492492676, "identity": 0.638069748878479, "hypothesis": "De deur 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_Jealousy_and_Envy/a86fe9611be218c9215f2c81a51976a5994eae30fab949273debd441ae7cbc2a.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "43b40bbde509b8569c9893002f5e0cc510418598f730259c6916281f66ca0c41", "generation_seconds_batch": 20.82914017001167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 5.927301406860352, "genuineness": 3.8671910762786865, "identity": 0.5590133666992188, "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_Jealousy_and_Envy/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "a8d4a85583b3344e736b8178f8349da36350bb00922246c95952972e2ee68729", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "39b1acfb7a012b08a41f261058ef12047e873ef463d54b4f2f00316166b0f678", "generation_seconds_batch": 22.870848860940896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.340320587158203, "genuineness": 4.268857479095459, "identity": 0.6187151670455933, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a8d4a85583b3344e736b8178f8349da36350bb00922246c95952972e2ee68729.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "a8e5775530736943a8c1365d50b1c7af16fb2d596c00bad66bcbdba3da260ef8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "508a34ddf46b6f44fad8a56681d837d47e24874d8145cba1670b4eb322896f24", "generation_seconds_batch": 17.110921034007333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 6.24500846862793, "genuineness": 4.287685871124268, "identity": 0.2665144205093384, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a8e5775530736943a8c1365d50b1c7af16fb2d596c00bad66bcbdba3da260ef8.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "a90455b48ee44b0ebec9b5909bfba1b8f1b857b6d395aa21934f0da7222d0215", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "52ef6e2ec3d9ad1c93fdd09290fdcedde9e804f32aee03218c7a07f11128dc83", "generation_seconds_batch": 25.390402112039737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 5.6413655281066895, "genuineness": 4.482243061065674, "identity": 0.5825478434562683, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a90455b48ee44b0ebec9b5909bfba1b8f1b857b6d395aa21934f0da7222d0215.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": "a9148bc44605e3d1b54a03fe49399e157ff60141a998fb5417f8f58e192bcd89", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "1499d95ca58d738d59ddbb04ad0d3586cc79427071c65195c18f11bea680923a", "generation_seconds_batch": 18.970201210002415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.732706069946289, "genuineness": 4.3127899169921875, "identity": 0.6406795382499695, "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_Jealousy_and_Envy/a9148bc44605e3d1b54a03fe49399e157ff60141a998fb5417f8f58e192bcd89.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "8171c9a99aca8f4131ebda8e6caaaa60e7832b7ce9ff225fc01fe2344030f52f", "generation_seconds_batch": 23.785890085971914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.213237762451172, "genuineness": 4.293961524963379, "identity": 0.7519149780273438, "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_Jealousy_and_Envy/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "a96149cb6a9c98fcb62b194b293d7cbfd20218872b53434704eae00a646aa48b", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "459288f369e0d80ddfea67d5eb87aa831876bcb9517fc81189eb8ca8e12d912d", "generation_seconds_batch": 19.141180579084903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 6.141753673553467, "genuineness": 4.770940780639648, "identity": 0.788060188293457, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a96149cb6a9c98fcb62b194b293d7cbfd20218872b53434704eae00a646aa48b.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "a971d8414ef26360f695444ef057ec754d8e4c092d16ccabc294f5adc30fe0bc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3e936c622d3f167743cde69f3599ce6210d53faa9c17d1cfe785afe0d76b406e", "generation_seconds_batch": 25.030283520929515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.395919322967529, "genuineness": 4.406930446624756, "identity": 0.667126476764679, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/a971d8414ef26360f695444ef057ec754d8e4c092d16ccabc294f5adc30fe0bc.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "aa47f6695fef4a4fdf8b8a815604895ead5ae5aaece647de839050bb4af23bfb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "285cf016d67c19edb4b2be41fcec99cc8aa7b174af593689b31c04e3d49b09ba", "generation_seconds_batch": 26.610086822067387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.149696350097656, "genuineness": 4.457139015197754, "identity": 0.5366131067276001, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/aa47f6695fef4a4fdf8b8a815604895ead5ae5aaece647de839050bb4af23bfb.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "aa95cb864cd7acae3ac1c06d2fac6cacf77adc230061a4491d6c792937127cae", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3fc7ce07f0ee0cc7626b964cc0b0331b43dfd9d51b70f1ad0901a12c90ff85ea", "generation_seconds_batch": 27.30863339896314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.117925643920898, "genuineness": 4.356721878051758, "identity": 0.5694596767425537, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/aa95cb864cd7acae3ac1c06d2fac6cacf77adc230061a4491d6c792937127cae.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": "aacf9af8dbd2905b831930bb993186dd8fb0e76f7ba1d04884e9cbd0cff74768", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "d52df09a3b6359e77c2baebd5f39f145d46a68acede93d3d8f39c1c2a3a8f375", "generation_seconds_batch": 19.23445519199595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0038815587759017944, "target_z": -0.4902343837489085, "ce": 6.0305562019348145, "genuineness": 4.375550270080566, "identity": 0.678901195526123, "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_Jealousy_and_Envy/aacf9af8dbd2905b831930bb993186dd8fb0e76f7ba1d04884e9cbd0cff74768.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "aae7d3553b56db332fb181a0851ac403278853e5bd431f598fd72e0f91d85ffc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3e5982e820dc3e865485eccf33c5653da2196a21a10536fdab26e5d1388b56fd", "generation_seconds_batch": 19.244287997018546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.111192226409912, "genuineness": 4.068024158477783, "identity": 0.7510939836502075, "hypothesis": "La puerta sigue abierta, me he dejado tu abrigo sobre la silla, dime cuándo estás", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/aae7d3553b56db332fb181a0851ac403278853e5bd431f598fd72e0f91d85ffc.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "ab0c155c2feb847e529798aaad8ea8b125ddb16996a6f13e5b3214c6115c553f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b3561e161532c68386c840bc1a3d78065a5c34124eba19332756841d2ab2e266", "generation_seconds_batch": 25.51136371702887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.6386703252792358, "hypothesis": "De deuren 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_Jealousy_and_Envy/ab0c155c2feb847e529798aaad8ea8b125ddb16996a6f13e5b3214c6115c553f.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "deeed0c60451e02c8933014f8d79cb3229e7020e00fe51b39a4bd0d540198201", "generation_seconds_batch": 17.480031306971796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 6.395919322967529, "genuineness": 4.381826400756836, "identity": 0.33623841404914856, "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_Jealousy_and_Envy/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "abf7b6dcd3948cd61f367c89e08d804778d04d1f18741cb5220c7f54428f2dec", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a128501fea171f1a68f72dabdb51a1c9c0d2e440aa6fe7834b0d103764401d4f", "generation_seconds_batch": 25.557199361966923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03007282316684723, "target_z": -0.41406249007586504, "ce": 5.839932441711426, "genuineness": 4.262581825256348, "identity": 0.7751280069351196, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/abf7b6dcd3948cd61f367c89e08d804778d04d1f18741cb5220c7f54428f2dec.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "ac253fb6aadaef81b1f3d0faa9dac4b53e17a1cf08de32e43959c91449742879", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7a128d298dfe0f66d8edd1869a61077b38a6010b0582c8cb8b608642f01a6f41", "generation_seconds_batch": 25.722407126100734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.372091293334961, "genuineness": 4.519899368286133, "identity": 0.23076969385147095, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ac253fb6aadaef81b1f3d0faa9dac4b53e17a1cf08de32e43959c91449742879.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "ad87bf1973f1c6e9e46b053e5913db20f157794c5a1d3e6ffd58f7ba00252163", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e8d82ebe8a9121188ed3db99105ebf33c06b7c4d7c651aa448967cb44e513ea4", "generation_seconds_batch": 26.75653860392049, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.4435701370239258, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ad87bf1973f1c6e9e46b053e5913db20f157794c5a1d3e6ffd58f7ba00252163.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "ada91029faf8ffd7d3fb1c0e88dabbb1ed5f36e322c39430e8ce7162d5b1e0e1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2fce4b4755acd2d077f4f9cc371311d864642e9d682160aa347e4802fa699e48", "generation_seconds_batch": 23.961409020936117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 5.935244083404541, "genuineness": 4.7834930419921875, "identity": 0.69886314868927, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ada91029faf8ffd7d3fb1c0e88dabbb1ed5f36e322c39430e8ce7162d5b1e0e1.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "adbf9224bac4243cf0cc158abb352c97ae4d41751a2551365a9374a9aa55856d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2abb7a694c2d3117d515c587432eba1c81e6c388f034ed221818fb27645b5442", "generation_seconds_batch": 19.62482622405514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.720792293548584, "genuineness": 4.2751336097717285, "identity": 0.3548648953437805, "hypothesis": "I found the little box. It was beside the old window. We can look inside", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/adbf9224bac4243cf0cc158abb352c97ae4d41751a2551365a9374a9aa55856d.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "64fdbb483cbe8bd04a440cb910ada85dc02fbbf407563d6c261b4f1ce2e101fb", "generation_seconds_batch": 18.83253820904065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.038498878479004, "genuineness": 4.394378662109375, "identity": 0.7162654399871826, "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_Jealousy_and_Envy/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "adfd5902a718dbf51e52172c5abdda8eaf44ecc6eb450d0d11cb81ae84460180", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "14b634f89b9adbe042e80328627c0590e45d5e326b1658e1bf58cacbad315401", "generation_seconds_batch": 23.453187841922045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.967014789581299, "genuineness": 4.507347106933594, "identity": 0.784638524055481, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/adfd5902a718dbf51e52172c5abdda8eaf44ecc6eb450d0d11cb81ae84460180.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "08ea247812fd5c964b760147752822081ce753aa3e2630d674b801dfaad2065f", "generation_seconds_batch": 23.559094437980093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.419747352600098, "genuineness": 4.243753433227539, "identity": 0.34274670481681824, "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_Jealousy_and_Envy/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "ae6d442f7bacc716d4466678dd7700f840da997dd6692043234555080461bc4d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "00430607ad2798799efe4f9598d19678667c707b51a91b05f86213bbf8452e4e", "generation_seconds_batch": 25.821169184986502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.252951145172119, "genuineness": 4.262581825256348, "identity": 0.643470287322998, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ae6d442f7bacc716d4466678dd7700f840da997dd6692043234555080461bc4d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "ae7652fee4e411d3424ee2225232f88f451a1f5828a49e28d5af139df3064729", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e036c86d88c9128618ddad2e5d045f2349825c266eb20810d4962e65024adbba", "generation_seconds_batch": 19.2782993450528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.022613525390625, "genuineness": 4.268857479095459, "identity": 0.43808072805404663, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ae7652fee4e411d3424ee2225232f88f451a1f5828a49e28d5af139df3064729.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": "af3a411639265deeae46ac9389a76181f2d054dd3bd6f303d755ca394c48946e", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f146f3bb56359f4118c20afbd82393a4befaff82c239c7493d8a0cb2da4c046d", "generation_seconds_batch": 25.261432219063863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.038498878479004, "genuineness": 4.369274139404297, "identity": 0.7236002683639526, "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_Jealousy_and_Envy/af3a411639265deeae46ac9389a76181f2d054dd3bd6f303d755ca394c48946e.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "af6c60db900a4e5cf487488b12a599fa78a2099b0b79aa06d9dabc9e7b63059c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6e3732266011a4b745f6ddd3a079f74aa81c5b51df49926df97dd759b6039580", "generation_seconds_batch": 17.856223818962462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.093321323394775, "genuineness": 4.137060642242432, "identity": 0.3311326503753662, "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_Jealousy_and_Envy/af6c60db900a4e5cf487488b12a599fa78a2099b0b79aa06d9dabc9e7b63059c.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "af7d42a315a5d58a834fd6829f5a774c861e40ff4bfc0cc6b3c6a16969a2a393", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "de7e6a227b8adda2ed48c62d19f66432efd6e17a49ab01a8e120bc16a3eb87dc", "generation_seconds_batch": 26.427332905004732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.109982967376709, "genuineness": 4.7458367347717285, "identity": 0.6737877130508423, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/af7d42a315a5d58a834fd6829f5a774c861e40ff4bfc0cc6b3c6a16969a2a393.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "af9f49ac73a96d896210d0cf2018a5834f5e9358dfa9e4574f1bcdb478aad5ef", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "21bfd32993ef4cb3cfe556ad8daa3b24c03809bf59f453d393985290a09d3840", "generation_seconds_batch": 30.387314268038608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030943438410758972, "target_z": -0.4121093868828458, "ce": 6.181467056274414, "genuineness": 4.7332844734191895, "identity": 0.7341812252998352, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/af9f49ac73a96d896210d0cf2018a5834f5e9358dfa9e4574f1bcdb478aad5ef.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": "afc46d929a65f5d4f3586308b52396dc7dfd26cf5aae091363e1d2033e964b0a", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2d9578f90aed7171ba99cacdbf0bd3a7175c5e15a5f326d1b3b20fc49ca0f84d", "generation_seconds_batch": 24.914569540997036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.696964263916016, "genuineness": 4.645420074462891, "identity": 0.743366003036499, "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_Jealousy_and_Envy/afc46d929a65f5d4f3586308b52396dc7dfd26cf5aae091363e1d2033e964b0a.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "b07c2dbae0ca2437886c0142df2947e2f3201e9c348925fd39e77245f5f59dda", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a345792853d35ebd0a4b132317bd86809ea7e0883c4419b9f9dee26f96edac8", "generation_seconds_batch": 25.02018914790824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 5.847874641418457, "genuineness": 4.375550270080566, "identity": 0.6497634649276733, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b07c2dbae0ca2437886c0142df2947e2f3201e9c348925fd39e77245f5f59dda.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "b0a0357dba2b6d63df4a6fd500674bacb5e4a3fc7307b4b2a2294655e9f0ca7f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "76c05f9840981d2fd8a4dd33f9a3072358b8877766a514b7aee6f4c9f34d4c68", "generation_seconds_batch": 18.76628469710704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.300607204437256, "genuineness": 4.413206577301025, "identity": 0.7558758854866028, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b0a0357dba2b6d63df4a6fd500674bacb5e4a3fc7307b4b2a2294655e9f0ca7f.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "b200b21e0a16139eb6dcfa8ec6ad26e05420125a52de551fd0b8cead3e3b3e3f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6258f6132e076b74e41bb30250398c94c3b280d7c5e0c4af492c51fc40043fae", "generation_seconds_batch": 27.66135234606918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.308549880981445, "genuineness": 4.218649387359619, "identity": 0.4634013772010803, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b200b21e0a16139eb6dcfa8ec6ad26e05420125a52de551fd0b8cead3e3b3e3f.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "b2af7f67e8bbb5110a853fd5507e48d47fcb47001c83bb45025a15179dd7c760", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "f2101d6eb9bd598b6c6efa43cf572b827bc8388031c74b64f3643f3091f89976", "generation_seconds_batch": 25.12381805595942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 4.854048252105713, "genuineness": 3.9299514293670654, "identity": 0.6605227589607239, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b2af7f67e8bbb5110a853fd5507e48d47fcb47001c83bb45025a15179dd7c760.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "b303e407eff8e9d42885d95be1d54e0baa1d1a04193398a85df4311e469f434d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9e600d0156502c5e4e2f7ab6ade1681b999879eba07946543652fea5f1d95c5a", "generation_seconds_batch": 27.1141992630437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 5.847874641418457, "genuineness": 4.846253395080566, "identity": 0.7230430841445923, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b303e407eff8e9d42885d95be1d54e0baa1d1a04193398a85df4311e469f434d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "b31e4bd5508ce0821bd1e9bf4ea3c698fb1d4412d7ae39055823c4c7ffd8300e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b87200e0ece0fed978471f81727cb01c6ad2702edefed4037064bc3f9367e78e", "generation_seconds_batch": 25.51136371702887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.046441555023193, "genuineness": 4.570107460021973, "identity": 0.691718578338623, "hypothesis": "De deur 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_Jealousy_and_Envy/b31e4bd5508ce0821bd1e9bf4ea3c698fb1d4412d7ae39055823c4c7ffd8300e.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "f5f796cf0c8dd0b01d8ecf1ab4397937bcaa1a89ace3ea8a4fa450052c4929bb", "generation_seconds_batch": 17.60779893491417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.38003396987915, "genuineness": 4.595211505889893, "identity": 0.6990969181060791, "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_Jealousy_and_Envy/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "b44d39c7e74cfc5b6763facbea509a02e4554a7c637e690bc3816c688fa6c8e9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "641675041d577a5400d83831ecbdc0f67c558c0fd71aa73800423aeab0dbc4a7", "generation_seconds_batch": 24.99562331789639, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 6.38797664642334, "genuineness": 4.193545341491699, "identity": 0.3868218660354614, "hypothesis": "The 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_Jealousy_and_Envy/b44d39c7e74cfc5b6763facbea509a02e4554a7c637e690bc3816c688fa6c8e9.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "b52956498c0b30397a80f79d5b8e01dea16fe8db55fa461367d859dde5513cea", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "14a90331423d48cef5f13ea807531e65cf87b0ffb7cb5c5d0b85943eb91b8047", "generation_seconds_batch": 25.028834199067205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.677107334136963, "genuineness": 4.432034492492676, "identity": 0.5325594544410706, "hypothesis": "De deur 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_Jealousy_and_Envy/b52956498c0b30397a80f79d5b8e01dea16fe8db55fa461367d859dde5513cea.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "b5f22228d400784d58d61cda80bd52354636dcdf2fcf570f56844088b3da7de8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "16b2e1809e2406774bcc5740545bfec40dc4b0edf44d1eab1b59fca979300804", "generation_seconds_batch": 17.96815433294978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.998785495758057, "genuineness": 4.582659721374512, "identity": 0.8516348600387573, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b5f22228d400784d58d61cda80bd52354636dcdf2fcf570f56844088b3da7de8.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": "b6444b21c3c0dd0c8cef7abd2d3358aaf77306e20cd23a3013e7e4dc64edb8b5", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The road turns left behind the bridge.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e22a45791bfc26321874aa238fe1b4d8257097c64d298d67da88f504d4bc7d32", "generation_seconds_batch": 25.25815057696309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.324435234069824, "genuineness": 4.494794845581055, "identity": 0.3807416558265686, "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_Jealousy_and_Envy/b6444b21c3c0dd0c8cef7abd2d3358aaf77306e20cd23a3013e7e4dc64edb8b5.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "b7678d137c16138a6c9d32b306c2c297a69b133fa895b19e557e644c20d8d709", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "70925c4f79f324378c26c9b890e96a8c6227263c44006f264d07beaa583f0615", "generation_seconds_batch": 25.178269008989446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 5.665193557739258, "genuineness": 4.419482707977295, "identity": 0.665456235408783, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b7678d137c16138a6c9d32b306c2c297a69b133fa895b19e557e644c20d8d709.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "b83270c6730478ecb7f776793a3d1698d813b75fb4ca10e63436973681f4cae3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "81cb01f52b2d557157c556deeb3435255e2d85e479e5ffd32404849b8f104c62", "generation_seconds_batch": 25.736650135018863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.696964263916016, "genuineness": 4.469690799713135, "identity": 0.61476069688797, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b83270c6730478ecb7f776793a3d1698d813b75fb4ca10e63436973681f4cae3.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "b857cbda1486ae8dbb434f252a5814d06af343c40a34a14ebe8eb109b453dd82", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9179a1ad487a232dd09f95a4e0d406d6fce5a5834bd9eb0b407adfc1fcf81606", "generation_seconds_batch": 24.044502418022603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.935244083404541, "genuineness": 4.3881025314331055, "identity": 0.7279553413391113, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b857cbda1486ae8dbb434f252a5814d06af343c40a34a14ebe8eb109b453dd82.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "b8625f151191227ad2a6d664283932d459786d80944f1e7629d0c009246bae7b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6b136b5fe5a88ea4e776a60867704f974b8cffb29e478824981f170fdf81d135", "generation_seconds_batch": 24.979949443018995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.34873491525650024, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b8625f151191227ad2a6d664283932d459786d80944f1e7629d0c009246bae7b.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "b89c6689166ae0a83047a463536cc49085425f620440d8ec43d02a073a3fbee0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6b3b9877c132a4658c3b367672f23cd7a2df292dbfb7272b7d9e2c48159fa818", "generation_seconds_batch": 19.691760155954398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.772419452667236, "genuineness": 4.319066047668457, "identity": 0.5984979271888733, "hypothesis": "De deur 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_Jealousy_and_Envy/b89c6689166ae0a83047a463536cc49085425f620440d8ec43d02a073a3fbee0.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "b91024d3843ab754662738d750e5b58ea0790036c45d3f4e46e85d6fee6dbddc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0cd5f7bdfe508bccf7bfd11a518736fa8c06c9d3b1ee2485e0b09b9ed6605b21", "generation_seconds_batch": 25.779991761082783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 5.982900142669678, "genuineness": 4.545003414154053, "identity": 0.6407137513160706, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b91024d3843ab754662738d750e5b58ea0790036c45d3f4e46e85d6fee6dbddc.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "b995f2ac673bfff4d822787db5a20057f0292696b96cf8557ea4c1001c18dd87", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5c4a2ff61e011efdd7d154fdb496723c91caedb425ffb26b42eee9c096195aab", "generation_seconds_batch": 25.641789675923064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.696964263916016, "genuineness": 4.68307638168335, "identity": 0.6508334875106812, "hypothesis": "La porte s'est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/b995f2ac673bfff4d822787db5a20057f0292696b96cf8557ea4c1001c18dd87.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "b9f754ed14f5914370e5ad2f91cf4912502719a015579d6ea95d31e4a5031439", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "740af458032cf46bbc5eb4078a30c3fccd63bc46e28183181e3383b85112bc4c", "generation_seconds_batch": 24.9541382570751, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 6.006728172302246, "genuineness": 4.457139015197754, "identity": 0.7329580187797546, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "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_Jealousy_and_Envy/b9f754ed14f5914370e5ad2f91cf4912502719a015579d6ea95d31e4a5031439.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "e34b369a4391c70d6e72540b07caf8c39cffab2f72a39b1a6e12114a35d4a3d0", "generation_seconds_batch": 18.796253976994194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.332377910614014, "genuineness": 4.469690799713135, "identity": 0.7602759599685669, "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_Jealousy_and_Envy/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "ba79c3c8a366784878ae59afbde429e5fa97dbe270b101a0f4e7601423d2eb37", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c25bbd115ba579da07ce1e01c0d7601afb65d89b9818daa0fcc13a5d9326e399", "generation_seconds_batch": 24.743595986044966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.062326908111572, "genuineness": 4.218649387359619, "identity": 0.6785791516304016, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ba79c3c8a366784878ae59afbde429e5fa97dbe270b101a0f4e7601423d2eb37.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "ba8bfc42f5582bb6bde7129ad10cc2e218a32abc0a5c6aa4c71339c11f38f42d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4dd61e329e501d364edb7bfd971f02cf2a186b2256f9b44ec47350bc32eecdc3", "generation_seconds_batch": 26.526089192018844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.967014789581299, "genuineness": 4.13078498840332, "identity": 0.6662979125976562, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ba8bfc42f5582bb6bde7129ad10cc2e218a32abc0a5c6aa4c71339c11f38f42d.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "ba912f8145569ac50160cffa8e06473ae97f2f0afc16bfcae4f9d002c9d1a15c", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3dad9e5ab7fd8615e7e42451d2cb84b5976927b41b9df8e2b5fb4a42c4e07b37", "generation_seconds_batch": 17.790779095957987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.3641486167907715, "genuineness": 4.3881025314331055, "identity": 0.4926653504371643, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ba912f8145569ac50160cffa8e06473ae97f2f0afc16bfcae4f9d002c9d1a15c.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "baa3edcdd788373518f18193e864d110405c3e39530663b552dcde58f8dcd6ed", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "75f68e4ffc0b9ad3572e05c76c1c3037d3be4bddc0fb85f4f088b167e830fc30", "generation_seconds_batch": 24.99286378803663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.027388423681259155, "target_z": -0.5429687382477348, "ce": 6.173524379730225, "genuineness": 4.055472373962402, "identity": 0.5196442008018494, "hypothesis": "I found the little box. It was beside the old window we can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/baa3edcdd788373518f18193e864d110405c3e39530663b552dcde58f8dcd6ed.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "bb1a7119bd4e2cfe3734b339e0e7b4e151346ae9a06fbf380e4bd77d0efc9056", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "df59b233747a26042189996a717d8cfa6ee1715e72686a547c6cead3b8c5d503", "generation_seconds_batch": 24.997460941085592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.137005805969238, "genuineness": 4.18726921081543, "identity": 0.4888729155063629, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lejos.", "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_Jealousy_and_Envy/bb1a7119bd4e2cfe3734b339e0e7b4e151346ae9a06fbf380e4bd77d0efc9056.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "bb534daa3e89143356108e8d5cc2ce3bd06ccb401441215998bb9cb340e336d6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fe3071a6956d570e0528fd54ba659c23466327c9f89ca121b8fd8d6ed4e2c55f", "generation_seconds_batch": 25.368129769922234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.205295085906982, "genuineness": 4.595211505889893, "identity": 0.37172678112983704, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bb534daa3e89143356108e8d5cc2ce3bd06ccb401441215998bb9cb340e336d6.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "bb7ecb5dcffc3e63e0263ae3cdf069bd9292fa9f0890c3638ad6081300f456dd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8cc0da69a6bb5e9b441dd88053cda724fc171e6d1e47fe4c248a7f8794f872bd", "generation_seconds_batch": 25.022231738897972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 5.824047088623047, "genuineness": 4.406930446624756, "identity": 0.7536222338676453, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bb7ecb5dcffc3e63e0263ae3cdf069bd9292fa9f0890c3638ad6081300f456dd.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "bb8c544ee38d2d7d8f4d1d266537acad2a156b4e396fa36a522b169618139bde", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b3a228745f3c7dd4956b1ad44b12b13c6fd4b4db3f4158fb276d31d0fcb3c846", "generation_seconds_batch": 19.490630768006667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.974957466125488, "genuineness": 4.432034492492676, "identity": 0.5124697685241699, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bb8c544ee38d2d7d8f4d1d266537acad2a156b4e396fa36a522b169618139bde.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "bbbad115e5d68cbbce85101402a7697373b3e5d50da3722721e3ea51335a1d2e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1b150c58679cf84a55c4a01c9d02c6ca5acdc48617e3515e1ca16b7d8fc11f6f", "generation_seconds_batch": 24.997460941085592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.262103080749512, "genuineness": 4.243753433227539, "identity": 0.6742372512817383, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bbbad115e5d68cbbce85101402a7697373b3e5d50da3722721e3ea51335a1d2e.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "bc35573475bbba88326adccfadee0fa3c83a5f3be536649cdd9da8b894915891", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8317fd8d360e0719b03378966e702ce6d184a51882e9093408b74413de811f71", "generation_seconds_batch": 25.375458125956357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.935244083404541, "genuineness": 4.582659721374512, "identity": 0.635270357131958, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bc35573475bbba88326adccfadee0fa3c83a5f3be536649cdd9da8b894915891.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "bc4a7a04e743699d5713b31d08e0377ce7452bab4a9da99487e664e35a30636c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2e3a50e0f19af7776b6b79f61b26f25b849517d7fdf5c759724b5ed9de7bdf5d", "generation_seconds_batch": 25.810610112035647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 5.6254801750183105, "genuineness": 4.369274139404297, "identity": 0.42676812410354614, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bc4a7a04e743699d5713b31d08e0377ce7452bab4a9da99487e664e35a30636c.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "bc940567a449ca70fefebe960f83f54eea23fdb06dd3fcf6c2f055c56f9c1457", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ce29dacb180517e7ecbb7833c07316c79b5b66043ba03ddbf00418a5ff2dc6fe", "generation_seconds_batch": 25.702681162045337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 5.967014789581299, "genuineness": 4.469690799713135, "identity": 0.2860073447227478, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bc940567a449ca70fefebe960f83f54eea23fdb06dd3fcf6c2f055c56f9c1457.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "bcd6e711599faf73cabf3ae3505782f862e7a8ab04cef88e3a31e061c1427533", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "185f5cfab207a3f0e863547fb29089161030a851a980515878b4b431d8c2257b", "generation_seconds_batch": 18.080471908091567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 5.9431867599487305, "genuineness": 4.381826400756836, "identity": 0.48859119415283203, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bcd6e711599faf73cabf3ae3505782f862e7a8ab04cef88e3a31e061c1427533.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "bdc81d26a152ba1032f04b2879f244fe21d97c316cf46ce34c158ea5a137f146", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f6ebebafc9ab5d68954cef141105efc3f1ff4358da8753e592cf00c64ddcc754", "generation_seconds_batch": 28.89545063301921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.260893821716309, "genuineness": 4.21237325668335, "identity": 0.3036767244338989, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bdc81d26a152ba1032f04b2879f244fe21d97c316cf46ce34c158ea5a137f146.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "bef7545ef10e7513c4c70e5109005ecc502195330a44e12019b7f1b3a979e74c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "75b38fa470e005b5cde13282425ca83f45d5576bcfd44af35d1bfd2805cdf363", "generation_seconds_batch": 28.051124901976436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.41180419921875, "genuineness": 4.6956281661987305, "identity": 0.21166405081748962, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bef7545ef10e7513c4c70e5109005ecc502195330a44e12019b7f1b3a979e74c.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "bf6e7a4ca391ff2223a77322154a50b53d7c17371bbdefc7fa562a28b5ad1cff", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "876972f28f8b407b38c3f0ee1a6eec607b4e4ba895f2cd7046c182096b0d55a3", "generation_seconds_batch": 24.942226220970042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.24500846862793, "genuineness": 4.381826400756836, "identity": 0.3453581631183624, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/bf6e7a4ca391ff2223a77322154a50b53d7c17371bbdefc7fa562a28b5ad1cff.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": "c03d2138e038868d38f989322fd9373754e683d812da29f94bff6c404b9539c8", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Escribí el número en el sobre.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "7daed5ef6b265057f03710ddbbd011e360031e4daa8f1cdaf347f0a5af9a0b5e", "generation_seconds_batch": 18.995592257007957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.8875885009765625, "genuineness": 4.607763767242432, "identity": 0.6652808785438538, "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_Jealousy_and_Envy/c03d2138e038868d38f989322fd9373754e683d812da29f94bff6c404b9539c8.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "c067366a488c9b9af2ce1f49997530be06c6b800c93a062fd481f085b79cb063", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3b0fe3a2178d46b997fd9a2fd37aa547cda3144291470a67ae45c0041b26286c", "generation_seconds_batch": 25.699113292968832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.752562999725342, "genuineness": 4.65797233581543, "identity": 0.6902979612350464, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c067366a488c9b9af2ce1f49997530be06c6b800c93a062fd481f085b79cb063.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "c074ba2d54e651eaeba1bf2fec5db19ab114428b0a76a2e99cd4bcf3ea9687c1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fe522c05991f596b0624e8459dc183791def88825dd2dae0da14a8bb05774353", "generation_seconds_batch": 25.727097783004865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.015199676156044006, "target_z": -0.5156249926874795, "ce": 5.023822784423828, "genuineness": 4.149612903594971, "identity": 0.6577559113502502, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c074ba2d54e651eaeba1bf2fec5db19ab114428b0a76a2e99cd4bcf3ea9687c1.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "c19c3edce8a6f5ad121415c461fd33abddc1c0fac9628c3fd5959b52cdaa9fe5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ccbb75ea418ecd1c7dab750930341013d958a1ccc1f677309aa3cb370d0e350a", "generation_seconds_batch": 19.534236458013766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.510311126708984, "genuineness": 4.519899368286133, "identity": 0.7448004484176636, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c19c3edce8a6f5ad121415c461fd33abddc1c0fac9628c3fd5959b52cdaa9fe5.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "c260d933c3c5fa5f2c3330e38dfe9babdbe3b74773775c2b62bd988e5d6bfe82", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "74ebd6ae786b7520d394a4180c893c5bd2bfe8f3879e887e546f2191eb79ea0a", "generation_seconds_batch": 23.178744758013636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.165581703186035, "genuineness": 4.68307638168335, "identity": 0.49636393785476685, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c260d933c3c5fa5f2c3330e38dfe9babdbe3b74773775c2b62bd988e5d6bfe82.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "c28f550e0984c5f4f1a8a71c276f327b3ca817e5bdc9abcdaffa1932a56510a1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a371df7fae1d0191d639c97a26883c13f2eb2c3e488df5dac7131f6d0261a83d", "generation_seconds_batch": 25.0568349219393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029202193021774292, "target_z": -0.4160156266975494, "ce": 5.927301406860352, "genuineness": 4.369274139404297, "identity": 0.6224647760391235, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c28f550e0984c5f4f1a8a71c276f327b3ca817e5bdc9abcdaffa1932a56510a1.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "c345321a6f5813138e62e486e6389eb5988fa2acfbadabd53bef6551767df9ef", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9ac7d692d4c0c1b5e353fa5484ce71f11d91c83163d085e5a12e6486bd96930a", "generation_seconds_batch": 25.20974485890474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.086154937744141, "genuineness": 4.545003414154053, "identity": 0.8154531717300415, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c345321a6f5813138e62e486e6389eb5988fa2acfbadabd53bef6551767df9ef.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "c35192ea0de50e3ea021c31298d9df69e5ab2750b75b2f7330757964a686e068", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4d794ea8167552967a769ea21c54a84002b7b1a2db92f4596ec7e16ae1edb103", "generation_seconds_batch": 26.380755561054684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.526196479797363, "genuineness": 4.7458367347717285, "identity": 0.8540209531784058, "hypothesis": "J'e 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_Jealousy_and_Envy/c35192ea0de50e3ea021c31298d9df69e5ab2750b75b2f7330757964a686e068.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e9fb53a615345f1bb8f0aa61774e42f5c50cfaa9898ec7473521ea86d73a441c", "generation_seconds_batch": 18.624153074924834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007364049553871155, "target_z": -0.4980468633783156, "ce": 6.348263263702393, "genuineness": 4.494794845581055, "identity": 0.5337775349617004, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "c3e6f3f1808d1426f25a1648b40e15f0cb8d461d51282bd06096ae902026c038", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1a2354e30f5971583b1d7ca74f0556c4c3797600d80a99fe7fc4881cd7a14d84", "generation_seconds_batch": 23.64291230100207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.181467056274414, "genuineness": 4.519899368286133, "identity": 0.2900698184967041, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c3e6f3f1808d1426f25a1648b40e15f0cb8d461d51282bd06096ae902026c038.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "c4035437223283956b6084822b76e29cc52d28dbff2f196e0735b44d648e2750", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d4e3f52612cada69053f4981e0cbf7a1f3c5ce036e4301e914171c2c283d76e8", "generation_seconds_batch": 29.87926796497777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 6.109982967376709, "genuineness": 4.413206577301025, "identity": 0.6198118925094604, "hypothesis": "De deur 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_Jealousy_and_Envy/c4035437223283956b6084822b76e29cc52d28dbff2f196e0735b44d648e2750.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "fad4b93b67614e79e63ff0ff0e916439a8e0b1dfc85e92398f987c32f37b3206", "generation_seconds_batch": 19.787600410054438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 6.141753673553467, "genuineness": 4.331617832183838, "identity": 0.7434982061386108, "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_Jealousy_and_Envy/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "c51a3d6bd1bb63a0ec3ace6d08648649d1fef2b82ff3d83715057977f2bbe575", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9d2d7310fe1a5c82af44ec87d1e4fd032d911c47a4821bafd587bc91ab7a0a6b", "generation_seconds_batch": 25.844160195090808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.8875885009765625, "genuineness": 4.7834930419921875, "identity": 0.7718367576599121, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c51a3d6bd1bb63a0ec3ace6d08648649d1fef2b82ff3d83715057977f2bbe575.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "c599b05956db146a43a76674a3f9bcec66e6f93c4969c56fa90dfab2d1d607f2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c8ecfbf9bcfc9a10844b96cc6a971bc63f5c226a81a978a671ec41ff3e5c4cc7", "generation_seconds_batch": 18.891782106948085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.23706579208374, "genuineness": 4.6203155517578125, "identity": 0.716575026512146, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c599b05956db146a43a76674a3f9bcec66e6f93c4969c56fa90dfab2d1d607f2.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "c62b9453f9a88983e22b12ac6c85fd30f94bed6e9123d78f60082e738151ce5e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a2afa38e4173392d9532c36c99b1fb3be8f2e39192e79d7ccaea20e80526f2da", "generation_seconds_batch": 30.387314268038608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.09409761428833, "genuineness": 4.381826400756836, "identity": 0.6555125117301941, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c62b9453f9a88983e22b12ac6c85fd30f94bed6e9123d78f60082e738151ce5e.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "c6816c88be8dded02fa1edb849958d051b9729be9ec7293c934ffe140bfc65d4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "71890263a5f47cc287f17c23f11758a93024616af98b21ac56560e731d5bcfbc", "generation_seconds_batch": 25.484098410001025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 6.046441555023193, "genuineness": 4.582659721374512, "identity": 0.6738130450248718, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c6816c88be8dded02fa1edb849958d051b9729be9ec7293c934ffe140bfc65d4.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": "c6cae8deaebecf97f7606512d1be55bc23085c777579a34ef975eb338daf2324", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "8ac50791ea19c178c8b9263cca472d29fadb80065ab21aca8f703e442b1fff11", "generation_seconds_batch": 17.040104218991473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.756534099578857, "genuineness": 4.632867813110352, "identity": 0.5023131966590881, "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_Jealousy_and_Envy/c6cae8deaebecf97f7606512d1be55bc23085c777579a34ef975eb338daf2324.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "c6f95f04405026c085c82574070c32b6c571069b67c1a8e124f1577f3de7d46a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e036ffa4b7e9303fe138a59a3494afa85e17b24f3c9e80aab218d7dc0dfe1032", "generation_seconds_batch": 25.265861809952185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.3842763602733612, "hypothesis": "The 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_Jealousy_and_Envy/c6f95f04405026c085c82574070c32b6c571069b67c1a8e124f1577f3de7d46a.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "c80006fbfbc09b1eecaa873f56f0f2be218547110103db6d0a38f4f2ae1a1f8e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "25f7e3b2f8037ccec7a09f0de4793981c34660bddadf9dbeed0f4e80601df1d6", "generation_seconds_batch": 26.329743598937057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 5.010915756225586, "genuineness": 4.18099308013916, "identity": 0.6742754578590393, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c80006fbfbc09b1eecaa873f56f0f2be218547110103db6d0a38f4f2ae1a1f8e.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "a07914974af301d7d0ecf8b64c49cec81e5cf70926861f708bac64d6d08860e4", "generation_seconds_batch": 18.83253820904065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.229123115539551, "genuineness": 4.218649387359619, "identity": 0.5288628339767456, "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_Jealousy_and_Envy/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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "0d17dab99759c17a4396e7f76cb3ac28bab86b6c70e4225cad407b777b611fe1", "generation_seconds_batch": 18.96070029598195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.403861999511719, "genuineness": 4.507347106933594, "identity": 0.37469184398651123, "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_Jealousy_and_Envy/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "c8cdbcc1522d760cc255014b10c5794cb2a56cdb5786a5ea682ba44ab3a35bbe", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "eca1d7e2bc47d43734ed8bc65360881782c2f30e8f2dd960b2d0f7b1b576ab86", "generation_seconds_batch": 30.36772264796309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.348263263702393, "genuineness": 4.256305694580078, "identity": 0.7116225361824036, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c8cdbcc1522d760cc255014b10c5794cb2a56cdb5786a5ea682ba44ab3a35bbe.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "c990274639093094cccd124c903cdc209704bf946cbd42d03f501c3d84ed55c4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e5df1b6dd300aad04c3d50ad38d4a46e2adb7c961b352df634bd1968fe861ca7", "generation_seconds_batch": 19.74051514500752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.855817794799805, "genuineness": 4.362998008728027, "identity": 0.37096983194351196, "hypothesis": "De deur 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_Jealousy_and_Envy/c990274639093094cccd124c903cdc209704bf946cbd42d03f501c3d84ed55c4.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "c9f27e963f254ef079fcac1095aed71d6ccfc0a1cd4076e71f791cc1b9273dbd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4a8a12853c3b1a567233a03c0d0ab9c4243b14ea5b7de856f600c085abd279c6", "generation_seconds_batch": 24.78775116696488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.229123115539551, "genuineness": 4.381826400756836, "identity": 0.6550844311714172, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/c9f27e963f254ef079fcac1095aed71d6ccfc0a1cd4076e71f791cc1b9273dbd.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "ca1f3d495aa58e354f37bb3f3b012f80dfd207f00b5a5fa35d48d379812d1421", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "25dd5f7a4c0791e10b5d41999ac32258693cc19910ad169d7c9689365debbda8", "generation_seconds_batch": 19.66635363304522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.173524379730225, "genuineness": 4.400654315948486, "identity": 0.5906268954277039, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ca1f3d495aa58e354f37bb3f3b012f80dfd207f00b5a5fa35d48d379812d1421.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "caa04e0d6e60f746e3caacaf37890357861c0cb9d20fc997080280f9137a621d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e8c08ca4a87846ac3de1c6d7f8123923f8716c97a43049e10824337198d43e83", "generation_seconds_batch": 26.190702778985724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.414999485015869, "genuineness": 4.325342178344727, "identity": 0.7658870220184326, "hypothesis": "la puerta sigue abierta he dejado tu abrigo sobre la silla dime cuándo estás libre", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/caa04e0d6e60f746e3caacaf37890357861c0cb9d20fc997080280f9137a621d.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "cb2d2529ff5d0a8a53be360ae3f7c586cb81f24b7b5c540cb18e9cbe460c986b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2bd456f8b8e25b86a9cbe8b9368ac67dd1faf8f30adea428bf9012813f10a2b6", "generation_seconds_batch": 25.844160195090808, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03181406855583191, "target_z": -0.4101562502611614, "ce": 5.839932441711426, "genuineness": 4.545003414154053, "identity": 0.7747472524642944, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/cb2d2529ff5d0a8a53be360ae3f7c586cb81f24b7b5c540cb18e9cbe460c986b.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "cb3c2a2f64ddba8b15b78f947fc3b011f03a67c494ba77b55a4288178bd4faea", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "073237120cf63b0bb2c669cab9aea4e766506b58a666f13cd255515b76daf8d5", "generation_seconds_batch": 22.666620434029028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 5.557967185974121, "genuineness": 4.519899368286133, "identity": 0.8256365656852722, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/cb3c2a2f64ddba8b15b78f947fc3b011f03a67c494ba77b55a4288178bd4faea.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": "cb6656dfc0f554097ce8c6e3a355c3b96bd4874e8ef157d02bc37fe9e0f263c8", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Someone moved the little blue chair.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "024d0bd427560bb635ea7a60372a42074c8986800b170e4bf98b77d1a1a884a0", "generation_seconds_batch": 25.21777619002387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.300607204437256, "genuineness": 4.519899368286133, "identity": 0.3963819146156311, "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_Jealousy_and_Envy/cb6656dfc0f554097ce8c6e3a355c3b96bd4874e8ef157d02bc37fe9e0f263c8.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "cbd965e25833b9dc28966373709f5d3631dcfbf2472ee8181cfd5bd46c8c2e5f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "46bb1277c04bbef3069642a45e0a7d5194d44c6765f085e486281717183ac853", "generation_seconds_batch": 18.87013247795403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.967014789581299, "genuineness": 4.570107460021973, "identity": 0.6503735780715942, "hypothesis": "De deur 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_Jealousy_and_Envy/cbd965e25833b9dc28966373709f5d3631dcfbf2472ee8181cfd5bd46c8c2e5f.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "cc0e936842d769090861b8803ae9a982366b82d95cc6e745f2425b4f90c7513d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cf413c15e0457cf94834d16085b3e5806398964f36d37df5c212b445a61500e1", "generation_seconds_batch": 25.910008443985134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.356205940246582, "genuineness": 4.086852550506592, "identity": 0.6382948160171509, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/cc0e936842d769090861b8803ae9a982366b82d95cc6e745f2425b4f90c7513d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "cc3bf00046b3c94d9fe718f32fd893aa2b6c27815ecb9adcf217ed8cb57af14f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c93863a0187e5427a3d5adbea4443d3b1b641eb71764683e55074612cb7cbad5", "generation_seconds_batch": 23.604830770986155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.695436954498291, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/cc3bf00046b3c94d9fe718f32fd893aa2b6c27815ecb9adcf217ed8cb57af14f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "ccafda1baa9e99eb080ab056954094de52fa68fa9821644221742819ce6d5860", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0bbfcd888188b6c8d7f0bb641b70d29522f39e7817a4fb42666d3a4a7cfe99cb", "generation_seconds_batch": 25.313193829962984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.165581703186035, "genuineness": 4.557555198669434, "identity": 0.8501226902008057, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ccafda1baa9e99eb080ab056954094de52fa68fa9821644221742819ce6d5860.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "cd34f7d78ff93beb3c25d76104d85dcef4933720ae1003c6d340993f7f90189a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "79883123faf36a3ded1d12f51ef3d7ab8e4b07eda9141375926a985663c67668", "generation_seconds_batch": 24.219958013971336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.555099368095398, "hypothesis": "De deur 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_Jealousy_and_Envy/cd34f7d78ff93beb3c25d76104d85dcef4933720ae1003c6d340993f7f90189a.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "cd618c102149b9389101a9ef89e25e2eeae924498d992b7e7ea2dff7172b824e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b249fc08103e5ca4d68b68033335c6c6a1176f914c8bced8cf011a2c87c09e4d", "generation_seconds_batch": 24.61209334305022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 5.871703147888184, "genuineness": 4.419482707977295, "identity": 0.6946753263473511, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/cd618c102149b9389101a9ef89e25e2eeae924498d992b7e7ea2dff7172b824e.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "cd7c53d5d95b201f1a5a850ce5dd8b2603451a71fa90904090d8372bc1b4d1c5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ffdd8294b2d77a6447421083d4501c9ac8290992579b0a80b07d4fe59dda7f61", "generation_seconds_batch": 26.574682892067358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.125868320465088, "genuineness": 4.325342178344727, "identity": 0.49956968426704407, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/cd7c53d5d95b201f1a5a850ce5dd8b2603451a71fa90904090d8372bc1b4d1c5.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": "cd92c475b33195b95520b977f2e62eb216a61949dbd7e97a5734c9529f825653", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Escribí el número en el sobre.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "acbb8ce0e32ed723a224b04ee09f6302e4bc9213f8e55727b54196dbce523569", "generation_seconds_batch": 26.550525714992546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 5.764476776123047, "genuineness": 4.469690799713135, "identity": 0.8363484144210815, "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_Jealousy_and_Envy/cd92c475b33195b95520b977f2e62eb216a61949dbd7e97a5734c9529f825653.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "cdcd4d938b7f64915b22dffe7ddf8f4a4066dab4909ac2c21254bc873969eb6d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f5600b6ccf52fe90ad108dd41465051da05e9bd9dd959885c9d162551947bfa", "generation_seconds_batch": 25.786488558980636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.308549880981445, "genuineness": 4.168440818786621, "identity": 0.20952896773815155, "hypothesis": "The 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_Jealousy_and_Envy/cdcd4d938b7f64915b22dffe7ddf8f4a4066dab4909ac2c21254bc873969eb6d.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": "cdd9f5df67bef25ed65a841c1ed45ccbfce63b817d3588c3cf2f6a8416632e0d", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "770350c52b8574d94399f1f0d3c7ef17460ba821dd6fb24ced3a242ddc2070a3", "generation_seconds_batch": 19.449114572023973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 5.728734970092773, "genuineness": 4.457139015197754, "identity": 0.6179235577583313, "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_Jealousy_and_Envy/cdd9f5df67bef25ed65a841c1ed45ccbfce63b817d3588c3cf2f6a8416632e0d.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "ce375da1d896e0dda961ea4a46a189a44548c28916caf5af35d1bfa179a4229a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8a92002e117ebf1a533d36100472eeb7134e52634b928e78126b3c92a999fd13", "generation_seconds_batch": 18.530879847938195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.38003396987915, "genuineness": 4.356721878051758, "identity": 0.6936308145523071, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ce375da1d896e0dda961ea4a46a189a44548c28916caf5af35d1bfa179a4229a.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "ce69a3e381714562371915e1ab1a45b049ef38019c056d1dc146f082a1339448", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a0a0e825c123f9e7c6fc62f7b015dc9a476e7e657ab866835c939e5d8baa57af", "generation_seconds_batch": 24.843744238023646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.419747352600098, "genuineness": 4.494794845581055, "identity": 0.29626256227493286, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ce69a3e381714562371915e1ab1a45b049ef38019c056d1dc146f082a1339448.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "ce9561f57193961291f8fb0314eaec94a290a0ed7044067ab7ce41a9adecf80e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ff52e5ffedb45f363785f6858577f88f6845326900ee0fbeddeac4d69f01a417", "generation_seconds_batch": 24.92784259095788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 5.927301406860352, "genuineness": 4.758388519287109, "identity": 0.7924104928970337, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ce9561f57193961291f8fb0314eaec94a290a0ed7044067ab7ce41a9adecf80e.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "cf3e712ea10b8487a9fad0cf308c3dcefd2f685364be82e1a24040753f906fb6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "22d76d4792d1cd957100f1de1d3209e5f28c3f9a0b0bd1a0eeab5e59c582fb14", "generation_seconds_batch": 19.5866262819618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.117925643920898, "genuineness": 4.7081804275512695, "identity": 0.5778497457504272, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/cf3e712ea10b8487a9fad0cf308c3dcefd2f685364be82e1a24040753f906fb6.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "a634f282919f4bb425a285ddfd5776e91f336e3e0b49197cb218ffc7d73b25f6", "generation_seconds_batch": 20.640614871983416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.395919322967529, "genuineness": 4.331617832183838, "identity": 0.6040344834327698, "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_Jealousy_and_Envy/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.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": "cfac2f63e9841bc29d8c0e839a44f20fb4c80221c10cde154fb2a3c5fbe770e6", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b8566c537e6e006396893bb6e60df98376b81ec8913dfa647be0196234674a5", "generation_seconds_batch": 26.19890572503209, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.09409761428833, "genuineness": 4.545003414154053, "identity": 0.6052960157394409, "hypothesis": "Ik scheef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/cfac2f63e9841bc29d8c0e839a44f20fb4c80221c10cde154fb2a3c5fbe770e6.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "d0063bb489f052eafa52ee0322348dfe5200dcaeb96c1fe3c491c23370669ffd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3239eea1e1d64ebcbef74320a7c5667ddd6c3c2178bbaf6fa987f299fcefcfb8", "generation_seconds_batch": 19.03412283596117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029202193021774292, "target_z": -0.4160156266975494, "ce": 5.569881439208984, "genuineness": 4.68307638168335, "identity": 0.6075173020362854, "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_Jealousy_and_Envy/d0063bb489f052eafa52ee0322348dfe5200dcaeb96c1fe3c491c23370669ffd.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "ee3dbe100958157ec3e0fd27b629fc7d81ac4c8cc07c623ccb51e70c6f55a992", "generation_seconds_batch": 19.281523138983175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.38797664642334, "genuineness": 4.055472373962402, "identity": 0.34282875061035156, "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_Jealousy_and_Envy/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "heldout-nl-1", "language": "nl", "sentences": [ "De sleutels liggen op de keukentafel.", "Ik keek in de la... en daarna naast het raam.", "Neem ze mee als je weggaat." ], "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-nl-1", "key": "d1594553707fb0030229e28b94ca9e818bcf0b6fd8c8131cafdf6bf5ee3fac0e", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c207f693accb548b2c9c3426e313c75a84b347008d1ccf6d7e6e8bf9f831fbe2", "generation_seconds_batch": 25.05561585200485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 5.895530700683594, "genuineness": 4.325342178344727, "identity": 0.5172885656356812, "hypothesis": "De slotels liggen op de kokentafel. Kikek in de la en daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.18181818181818182, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d1594553707fb0030229e28b94ca9e818bcf0b6fd8c8131cafdf6bf5ee3fac0e.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "d163a56a573a674e352d68f7602c529028c664a76a57342a3719064f73c37e3c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bf655432bbabb6f327c7425b5566402e7d66d26b727ca86b14463760ae244226", "generation_seconds_batch": 24.271399033023044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 5.33954381942749, "genuineness": 4.425758361816406, "identity": 0.7300858497619629, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d163a56a573a674e352d68f7602c529028c664a76a57342a3719064f73c37e3c.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "d1ccb6c8fdd8f92450b41d2d6a9dc29a3667997b706db90cef320e4a72b3b8dc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "38f11fe77eebe15a33eb1151a08692876494d601b03acfc8ce897b5d9747d9b5", "generation_seconds_batch": 19.189722777926363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 5.708878040313721, "genuineness": 4.7081804275512695, "identity": 0.7949745059013367, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d1ccb6c8fdd8f92450b41d2d6a9dc29a3667997b706db90cef320e4a72b3b8dc.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "d1d80ba3e4fc971de8637456555c8e7be4c5943a52a52feeca9d41835bc920a3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c0de7dfaac5f12ec3aa96078b25bf0584cf9ea4678ad4941a8183f89ab1706c1", "generation_seconds_batch": 17.549577704048716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.117925643920898, "genuineness": 4.582659721374512, "identity": 0.6783994436264038, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d1d80ba3e4fc971de8637456555c8e7be4c5943a52a52feeca9d41835bc920a3.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "d1d957547ec1712018f1a567b156b9fbd74b12838fa31f91a14b5a64370ea651", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9dd82001f63b8d23d9b5be01cac120d9fbdb3a740a24ec1bfcf3705f3cc24494", "generation_seconds_batch": 24.743730827001855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 6.23706579208374, "genuineness": 4.325342178344727, "identity": 0.1258017122745514, "hypothesis": "The 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_Jealousy_and_Envy/d1d957547ec1712018f1a567b156b9fbd74b12838fa31f91a14b5a64370ea651.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "d20699bfaefaeacded3bd56efa1f4c44cfde2d2d8e60a9fffd0c94d311a8fe40", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "82abc4014525f4a242326c977bd3fc0f4d5daef1c1f4baeccf42e3f06a24ca93", "generation_seconds_batch": 24.450977499014698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.372091293334961, "genuineness": 4.293961524963379, "identity": 0.6392680406570435, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d20699bfaefaeacded3bd56efa1f4c44cfde2d2d8e60a9fffd0c94d311a8fe40.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "83b144e60eb338d45bf04c4e355edc3a6b9b1cc2352c0e8e10d6a9034a8f5f3c", "generation_seconds_batch": 20.12810609000735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007364049553871155, "target_z": -0.4980468633783156, "ce": 6.308549880981445, "genuineness": 4.306513786315918, "identity": 0.728966474533081, "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_Jealousy_and_Envy/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "d2654a46800caf663df1d60ec19a66e0eb26f5b757c1ba627accc1b711b7214b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fc7d9d26cd99a92051c17d3336800c264a762eb99a6e415135e704d48658f14b", "generation_seconds_batch": 19.485516358050518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.804190158843994, "genuineness": 4.457139015197754, "identity": 0.475482702255249, "hypothesis": "De deur 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_Jealousy_and_Envy/d2654a46800caf663df1d60ec19a66e0eb26f5b757c1ba627accc1b711b7214b.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "d26c72dc4893f087030bf1a3564c9725428b90b3998c0bd0290e19e69ed9df4b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "305aa90fc07202dbec8a676a845f7c24e382142e19f1f15274087c7632d48adb", "generation_seconds_batch": 26.74932188994717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.669164657592773, "genuineness": 4.017816066741943, "identity": 0.7519834041595459, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d26c72dc4893f087030bf1a3564c9725428b90b3998c0bd0290e19e69ed9df4b.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "d271461940bfe0e170f20894ae7843a615624f5410b4b18210ddc634dc2225aa", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b3dec278d0a9e4e2c6a0c4ba3bfb2b290555ffb1d02a069f5ffcf59b90ca1d20", "generation_seconds_batch": 25.733686294057406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.006728172302246, "genuineness": 4.6203155517578125, "identity": 0.5464999675750732, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d271461940bfe0e170f20894ae7843a615624f5410b4b18210ddc634dc2225aa.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "d329375f79315b2a149c567738af3d33662d307674c61329a9cf692f1610850a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2f0f892f2dce4268fd2a245a1c1b057330f6bc87d6bdc9912a66c2a7555e6ce6", "generation_seconds_batch": 25.72707874700427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.046441555023193, "genuineness": 4.65797233581543, "identity": 0.6215505003929138, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d329375f79315b2a149c567738af3d33662d307674c61329a9cf692f1610850a.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "d3e07ab859cb0ba835f7880aa1cb5c01098395626fdcd0d137dca0f1b9a8d1e5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9d2e74a6d17d06c2e9488821679305f963b226fc48578e0f07a83aa68bef47c1", "generation_seconds_batch": 29.818743888055906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 5.982900142669678, "genuineness": 4.557555198669434, "identity": 0.7725824117660522, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d3e07ab859cb0ba835f7880aa1cb5c01098395626fdcd0d137dca0f1b9a8d1e5.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": "d3f614dd39c6c93c2ba6730862567f4b0c0589e100c2a49e28b6234f4814280d", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "adff01fd4abc2bc057fc20044d48eb859e4d6cd5a4e2f0d093c8410de5223323", "generation_seconds_batch": 25.938403517007828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 5.518253803253174, "genuineness": 4.256305694580078, "identity": 0.5691062211990356, "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_Jealousy_and_Envy/d3f614dd39c6c93c2ba6730862567f4b0c0589e100c2a49e28b6234f4814280d.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "23eb43c0241710dd84fa0df94e41389ed612245af987ee40a725e3ce92cdd02f", "generation_seconds_batch": 18.765271497890353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.09409761428833, "genuineness": 4.444586753845215, "identity": 0.7984709143638611, "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_Jealousy_and_Envy/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "d464c8e9ab452a60d729c9f2f6fefa381b9f0fb091331215f9a2a5e898e1bbd3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a010a4ddc452d4d680ea3169cf1dbd9793a24c377517ff07588e0e1e1b056855", "generation_seconds_batch": 23.66483902791515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.197352409362793, "genuineness": 4.231201171875, "identity": 0.27940258383750916, "hypothesis": "The 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_Jealousy_and_Envy/d464c8e9ab452a60d729c9f2f6fefa381b9f0fb091331215f9a2a5e898e1bbd3.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "d46f00466888e84cd50361c668ac45eb3b639d43b91c4dfd31dc0d7549243252", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d3258f68bc497ee9b11db3c76911ecac8441d5f159edd1ad452d41fd998ad13a", "generation_seconds_batch": 25.35941005893983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.23706579208374, "genuineness": 4.519899368286133, "identity": 0.6100850701332092, "hypothesis": "De deur 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_Jealousy_and_Envy/d46f00466888e84cd50361c668ac45eb3b639d43b91c4dfd31dc0d7549243252.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "d4b46a156f83abb03f5c66b775a024ab8988ded73620c7708ad341eaf421a44c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5e63a24f6a1cbbc7bcd7f56bc864ee877334c3f6337abc6a87986014bdfc5f9f", "generation_seconds_batch": 24.376648970064707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 5.847874641418457, "genuineness": 4.469690799713135, "identity": 0.5284857749938965, "hypothesis": "De deur 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_Jealousy_and_Envy/d4b46a156f83abb03f5c66b775a024ab8988ded73620c7708ad341eaf421a44c.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "d5a1461d6ce6c718cc6beb3da8fef8c4bac76aa7b20ed2a4915b5695a201ce59", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7af1d762426d87a93645050eec95d0386245e2944876829754be103a3f7ea659", "generation_seconds_batch": 24.281332539976574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.696964263916016, "genuineness": 4.193545341491699, "identity": 0.790404200553894, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d5a1461d6ce6c718cc6beb3da8fef8c4bac76aa7b20ed2a4915b5695a201ce59.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "d5c56b0ab676a5820dc6d02e4bbdadb3071097dc5bf18db02c1c5fd15d88b450", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eb54b912a6a4568031c9f0dda4fb3124c54646926ba347a95c700868a0afbd98", "generation_seconds_batch": 18.473344001104124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 5.2223896980285645, "genuineness": 4.425758361816406, "identity": 0.6287271976470947, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d5c56b0ab676a5820dc6d02e4bbdadb3071097dc5bf18db02c1c5fd15d88b450.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "d66546194350032252b2bc6ef09d9c268841b7ef3b4fe0e121943c4896e1332f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "180c43fa6f3622a2ba90dfa46e2354b2842bf136f4763dbc97533fa6e388ce89", "generation_seconds_batch": 19.485516358050518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 5.752562999725342, "genuineness": 4.507347106933594, "identity": 0.4385317265987396, "hypothesis": "De deur 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_Jealousy_and_Envy/d66546194350032252b2bc6ef09d9c268841b7ef3b4fe0e121943c4896e1332f.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "d697c01f7876b35da935a37f4f79afbbbc730cd7b8d89d65d6caa04924ee5bef", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "08abd0556c0282a1efc013852ed2351cc6595815e6199cce5bddef200ebd1fd1", "generation_seconds_batch": 26.17577479290776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.839932441711426, "genuineness": 4.632867813110352, "identity": 0.6507280468940735, "hypothesis": "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_Jealousy_and_Envy/d697c01f7876b35da935a37f4f79afbbbc730cd7b8d89d65d6caa04924ee5bef.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "d6a7fc06c8c3f4f68987b28c6efd8824e67dbb0d1c9cafe69c212d45c4da373e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bb1286b27dd161d10f4f27ce25edefe74369e399be076c6db6db298b3f45d5b1", "generation_seconds_batch": 25.19380322797224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.070269584655762, "genuineness": 4.394378662109375, "identity": 0.5484064817428589, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d6a7fc06c8c3f4f68987b28c6efd8824e67dbb0d1c9cafe69c212d45c4da373e.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "d71b91fbd5ca4d9de1209c00a969101cc7ab61528628c5a25e30214c94ad23de", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "62f6435dfa49b605ba731ce91e66e2c256051f2efd0ad055412f309ecd1d53d1", "generation_seconds_batch": 24.69084544898942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 5.871703147888184, "genuineness": 4.419482707977295, "identity": 0.72749924659729, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d71b91fbd5ca4d9de1209c00a969101cc7ab61528628c5a25e30214c94ad23de.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "d818d1338891829aea9d8c3e9c6cff94e55c6e19b1d53a525bbc77ab394cc1ca", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8a5bd2b3a1711d91c1516e3bc0ba10d9b620c81220265c18a57d3f38b4b98767", "generation_seconds_batch": 25.560263633960858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.0146708488464355, "genuineness": 4.250029563903809, "identity": 0.6142188310623169, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d818d1338891829aea9d8c3e9c6cff94e55c6e19b1d53a525bbc77ab394cc1ca.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": "d828d2db984d38b443fe8dad6f5b01133468fd4349f8cfd4028c065b3ef55f59", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af45d850bd563e566319e3560d9591b7084683984985342da6905fe21521f283", "generation_seconds_batch": 24.686428055050783, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.673621654510498, "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_Jealousy_and_Envy/d828d2db984d38b443fe8dad6f5b01133468fd4349f8cfd4028c065b3ef55f59.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "d8b7aaf05b4931206580b990b058da82bbc064fa804c8644113b4d44ce3cea75", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "de26b566103b68d1dde19a3daabd474fcf273123c7dcd7a6ff7739aaee3dbfc6", "generation_seconds_batch": 25.950248078093864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.051621913909912, "genuineness": 4.758388519287109, "identity": 0.7878048419952393, "hypothesis": "Eh, con todo la cajita estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.17647058823529413, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d8b7aaf05b4931206580b990b058da82bbc064fa804c8644113b4d44ce3cea75.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "d9e0baaff590ecf1a2531a2e49a246246ff46d450c6c5904eeb2dc8497faa56f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99a59dbbfa3ac88ea46fd5d16aa5a96b918be1d6ea1530635a08517e1687030d", "generation_seconds_batch": 19.62482622405514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.1894097328186035, "genuineness": 4.645420074462891, "identity": 0.38480469584465027, "hypothesis": "I found the little box. It was beside the old window we can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/d9e0baaff590ecf1a2531a2e49a246246ff46d450c6c5904eeb2dc8497faa56f.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "da97e92ea72287294951e5400881504688f8cd059f965221cd77478d0df543de", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3af2679c099a734613b908c4bf1162e5c065239fa79f0f6c8b569e49bf266e48", "generation_seconds_batch": 25.983740528929047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 5.8875885009765625, "genuineness": 4.381826400756836, "identity": 0.5207765102386475, "hypothesis": "De deur 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_Jealousy_and_Envy/da97e92ea72287294951e5400881504688f8cd059f965221cd77478d0df543de.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "a70ad774cc3ee33537e616b36f39e43d6749e27ecf1ff91648cb246786ee6471", "generation_seconds_batch": 17.480031306971796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05183844268321991, "target_z": -0.3652343753917422, "ce": 6.562715530395508, "genuineness": 4.20609712600708, "identity": 0.3073180317878723, "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_Jealousy_and_Envy/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "db7e264f9485aa7a9f811b1bc9755460b2c14ef6b902a3dfa8988d7d71fc6eed", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e151edb1f9104c0aaf601b8f4c554937fcae7e1427ca966e96ec934d12c2d08b", "generation_seconds_batch": 19.189722777926363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.748591423034668, "genuineness": 4.68307638168335, "identity": 0.7609906196594238, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/db7e264f9485aa7a9f811b1bc9755460b2c14ef6b902a3dfa8988d7d71fc6eed.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "dbbaef94529143d953b707307b8367c909ea72963390a1bdebf70265938b7724", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1e4e6f9a7393397ddbad52cb3cc27bd1d4ce6cb834abaadc7ae4041c6e1dee36", "generation_seconds_batch": 19.141180579084903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.205295085906982, "genuineness": 4.7332844734191895, "identity": 0.7723479866981506, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/dbbaef94529143d953b707307b8367c909ea72963390a1bdebf70265938b7724.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "dbd7a89bdf9c3dd58cdaa8ee71877f80d74ceddbe66b6e739bc5ffa43798a492", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "40ecc48bf5e95685b350be18fc3c689745b8752e1acd9ae958acdccda53d504b", "generation_seconds_batch": 24.1138914990006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.09409761428833, "genuineness": 4.300237655639648, "identity": 0.19521774351596832, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/dbd7a89bdf9c3dd58cdaa8ee71877f80d74ceddbe66b6e739bc5ffa43798a492.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": "dc364def08dcc218a1fe2056ed7e1e7c18b47949accee832f585b380b44e312b", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The keys are on the kitchen table.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d76db57a0916dcfeed3a9abf69bb6ad2651d12a6d9dec27aeeb52e5783c4dca", "generation_seconds_batch": 24.68429503403604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007364049553871155, "target_z": -0.4980468633783156, "ce": 6.459460258483887, "genuineness": 4.406930446624756, "identity": 0.3088871240615845, "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_Jealousy_and_Envy/dc364def08dcc218a1fe2056ed7e1e7c18b47949accee832f585b380b44e312b.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": "dcd79c17683ac006695fe90fa2ca77a60fe99aecb7da8201ba948956e6b90bb9", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "4ea726e4e183c3993e3d32f523d9049de594e7c8887fa18a8ed0af5cec4675d4", "generation_seconds_batch": 21.57722077902872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.141753673553467, "genuineness": 4.808597087860107, "identity": 0.8665969371795654, "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_Jealousy_and_Envy/dcd79c17683ac006695fe90fa2ca77a60fe99aecb7da8201ba948956e6b90bb9.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "dd1ab35d216cf3ce12d653bd3bb13964b00813be6d959ee53aea82fab5a1de02", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "629ce62aea7fa8eed01cc8f613e25475cf1220fe02c9af6342a0d4b6d841c1bf", "generation_seconds_batch": 24.171800701064058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.324435234069824, "genuineness": 4.293961524963379, "identity": 0.32385897636413574, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/dd1ab35d216cf3ce12d653bd3bb13964b00813be6d959ee53aea82fab5a1de02.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "ddc5bdb44e2a4ebc99994cc0867f5c043e88f436fc7775a9262a1f76acadb162", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ccdc8ca83742d0af4e44d5579d688ead4993337335479dbce0d2a7a574288fca", "generation_seconds_batch": 24.93342735094484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03181406855583191, "target_z": -0.4101562502611614, "ce": 5.804190158843994, "genuineness": 4.111956596374512, "identity": 0.20702773332595825, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ddc5bdb44e2a4ebc99994cc0867f5c043e88f436fc7775a9262a1f76acadb162.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "df55d4331a383843aaf55f7ec1ae38e711cee1e48862f1557d626a69062dc23d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b127558212f09d1d0c4a731951f790167cfee7480712fe04449230876a9ffe61", "generation_seconds_batch": 25.77280287106987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 5.831989288330078, "genuineness": 4.413206577301025, "identity": 0.6353185176849365, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/df55d4331a383843aaf55f7ec1ae38e711cee1e48862f1557d626a69062dc23d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "dfae0074490245afcb1dc6646fbc5d46df6f5da2aff61031280072e0bbad44d3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8f93e29382bd7dd777060dfdbc2c5a1ab54f6c232d4234a00163de5c4f503f3a", "generation_seconds_batch": 25.641709838993847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025719687342643738, "target_z": -0.4238281397556217, "ce": 5.752562999725342, "genuineness": 4.482243061065674, "identity": 0.34087494015693665, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/dfae0074490245afcb1dc6646fbc5d46df6f5da2aff61031280072e0bbad44d3.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "dfc1c8ab21c3a5d0971215cf76aa3a4d882f551e9846c95ff0324524fbb32780", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7eee98d320a447fe9bdbeb09b0c1849bdde5492424773ae8d722023a597cd8b9", "generation_seconds_batch": 19.342694528982975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.268836498260498, "genuineness": 3.9425034523010254, "identity": 0.18159490823745728, "hypothesis": "The 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_Jealousy_and_Envy/dfc1c8ab21c3a5d0971215cf76aa3a4d882f551e9846c95ff0324524fbb32780.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "dfc9a6b01bddb18f68513c8962fa20443f00a0900b003e9de998ca4166835ec7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a2a6f65df15dfabfff5bc1908e37336fe149d16e475073c0aaf9c360ac5d1053", "generation_seconds_batch": 25.313193829962984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.6151108741760254, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/dfc9a6b01bddb18f68513c8962fa20443f00a0900b003e9de998ca4166835ec7.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "e09ec3b502cd151de1ac5ff4856f9e2538b845dac0ecea6f4a4dd0acc2db71a2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6f5555d95aa0d5fc9bca2044751f980a59aee59473aac40c532aad5ff780dfb1", "generation_seconds_batch": 25.647324160090648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028331562876701355, "target_z": -0.41796876331923377, "ce": 6.1020402908325195, "genuineness": 4.720732688903809, "identity": 0.625881552696228, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e09ec3b502cd151de1ac5ff4856f9e2538b845dac0ecea6f4a4dd0acc2db71a2.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "e0b29b6bdab0d664513b761bfcfb3de0724877e9d430c58e0893cbb3e6f73e65", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bc061af5a84db418b088b56a3a9a863dd2eb36e806d832937c03a627d6e4d0c5", "generation_seconds_batch": 24.80721532809548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 5.959072113037109, "genuineness": 4.482243061065674, "identity": 0.4213000535964966, "hypothesis": "De deur 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_Jealousy_and_Envy/e0b29b6bdab0d664513b761bfcfb3de0724877e9d430c58e0893cbb3e6f73e65.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "e0b5bbe50e79710f399cedc4ee615e1a6ab5d781081f9d9834e65d13c1d23668", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f9cb6c247f4ceaa882dfdee5dea2fa98939ce6451daff79319777af73dac2a13", "generation_seconds_batch": 17.930450039100833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.6254801750183105, "genuineness": 4.7081804275512695, "identity": 0.6651303172111511, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e0b5bbe50e79710f399cedc4ee615e1a6ab5d781081f9d9834e65d13c1d23668.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "e0d126880b79a4aa160ca17733955b3aff597385f8799c5e122dd2c24f13518e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "74f92232cceb04a85fdf319fa253c23e047948dd05e8435d18f82a762b4f9d7d", "generation_seconds_batch": 25.641789675923064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 5.561938762664795, "genuineness": 4.65797233581543, "identity": 0.7719882130622864, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e0d126880b79a4aa160ca17733955b3aff597385f8799c5e122dd2c24f13518e.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "e1e08cc089323213d0c4593bcc61faa894499e8cce16e70a69711b0699b86700", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d27c94e9e4d56d399bb4ad1cf36c324340fede151c2a0423d8380c64549945c9", "generation_seconds_batch": 23.94664634799119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 5.935244083404541, "genuineness": 4.319066047668457, "identity": 0.6892133951187134, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e1e08cc089323213d0c4593bcc61faa894499e8cce16e70a69711b0699b86700.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "e2059803e0c7a3ffe207ee0f9416743d9f82d6a0c068dadd17ccf3c02de4f426", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a6fde4887b620dc70bbcb4d57d5fee5869ca6ccd207f040e5f8d37e3708610b0", "generation_seconds_batch": 18.388860790990293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.982900142669678, "genuineness": 4.356721878051758, "identity": 0.6143207550048828, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e2059803e0c7a3ffe207ee0f9416743d9f82d6a0c068dadd17ccf3c02de4f426.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "e234f6dee63a69f23f920f830aeef8aaba84a30aa646a73300fc74036cb46d5e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b87e329d83a128274a42ec146f5955c5451fe4adb5c01d5deeaa9725a16b8976", "generation_seconds_batch": 18.62888325599488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.300607204437256, "genuineness": 4.362998008728027, "identity": 0.10167615115642548, "hypothesis": "The 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_Jealousy_and_Envy/e234f6dee63a69f23f920f830aeef8aaba84a30aa646a73300fc74036cb46d5e.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "e23d42be8417edb6f8b291eb3a7f343882c1f82b796be2c169dba31eb1e9a55a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "10aedcde5b4d4369197535fd7a546024a5823ffba9258f19b416625a9a3e55fb", "generation_seconds_batch": 26.213524178951047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.213237762451172, "genuineness": 4.808597087860107, "identity": 0.8030074834823608, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e23d42be8417edb6f8b291eb3a7f343882c1f82b796be2c169dba31eb1e9a55a.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "e320ed3cb4ce6ecf1987f821b876787e410e78b6448c9a892d4d9083b77c9ecd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bd823d8d46ecf798c5fbd66787c7c413d8532bfc5871d748788b356c02ceb8a", "generation_seconds_batch": 23.205528686055914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.542081832885742, "genuineness": 4.607763767242432, "identity": 0.684913158416748, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e320ed3cb4ce6ecf1987f821b876787e410e78b6448c9a892d4d9083b77c9ecd.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "e39ce00b0d8299b803a294ba764dbe96957e5d765503a0812d3cd69902a8dbc1", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "10850aaf919438facceeefa0e9dfe3932b0507737f235845a7586b8be208967c", "generation_seconds_batch": 19.130602285964414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.023978441953659058, "target_z": -0.42773437957032534, "ce": 5.4666266441345215, "genuineness": 4.545003414154053, "identity": 0.7772882580757141, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e39ce00b0d8299b803a294ba764dbe96957e5d765503a0812d3cd69902a8dbc1.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "e41cf604df5cfc976dc908c95f860ecfd1d4ac5db51ffad1c722575be5e7255b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dd1367af06728a9e85c0ffb1deeac055fcf80e7ae67bdbd11fa27c7df5b4332b", "generation_seconds_batch": 30.36772264796309, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 6.324435234069824, "genuineness": 4.444586753845215, "identity": 0.6873527765274048, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e41cf604df5cfc976dc908c95f860ecfd1d4ac5db51ffad1c722575be5e7255b.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "e49ae9d973d64e9954a8d657c848202b2e79317db31d3cab76dfb70615baedcc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0380510d9e5b0819e2d8e83d747f7fcc113248bdfe87f007df8dd9946cd96caa", "generation_seconds_batch": 19.717079291003756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.308549880981445, "genuineness": 4.419482707977295, "identity": 0.42003437876701355, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e49ae9d973d64e9954a8d657c848202b2e79317db31d3cab76dfb70615baedcc.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": "e49e142edc2d20cb2c5f2e95b6b9b8b17e6f04b63b9b279801edd4e28b92668a", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "366ed95236bdbe7834df5eb8fa107899ee76a726fdfdd9c94fc58660078a7e94", "generation_seconds_batch": 25.457687178975902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.006728172302246, "genuineness": 4.6705241203308105, "identity": 0.7377018928527832, "hypothesis": "Calcoin a deplacé la petite chaise bleue. Elle était ici, près de la grand bibliothèque.", "wer": 0.42857142857142855, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e49e142edc2d20cb2c5f2e95b6b9b8b17e6f04b63b9b279801edd4e28b92668a.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "e52ce96c97aad69b56652845fc4bed8cb038afa9262cc8316c8feb46d1c8bc0a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "52cfa6cd5ec70b88e225b16bb9306b20919a35db0afc78e0fb20fbf8fc8063b1", "generation_seconds_batch": 25.7998307159869, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.0305562019348145, "genuineness": 4.3504462242126465, "identity": 0.7780469059944153, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e52ce96c97aad69b56652845fc4bed8cb038afa9262cc8316c8feb46d1c8bc0a.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": "e556ef05ed8ec6688e7fd295f2c54f3c0c3de62b7a33876c1063957a57154f06", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "37d7722a8fdb36bc030ccf94c116bd7dd07a0f138cc762dd6931a3066828e3f1", "generation_seconds_batch": 19.239313781959936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.903473377227783, "genuineness": 4.796044826507568, "identity": 0.8629772663116455, "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_Jealousy_and_Envy/e556ef05ed8ec6688e7fd295f2c54f3c0c3de62b7a33876c1063957a57154f06.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "e557d982e11d7d0630299fc53f894c5a3ac19b6a32f95fdded140c5e249763bb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "38346ee8faa28e9cf1d9becbf594176c673f049781622305884f7ab3fa2763c1", "generation_seconds_batch": 23.53988604794722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025719687342643738, "target_z": -0.4238281397556217, "ce": 5.808161735534668, "genuineness": 4.6203155517578125, "identity": 0.7046022415161133, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e557d982e11d7d0630299fc53f894c5a3ac19b6a32f95fdded140c5e249763bb.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "e57e63a46df785611428d3bbaf957397795c9991d7d1e76cc9e37415544137ef", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e39ba2c4ccf8c1200e22b2c614bc0704fd86c9b8da4b91ddb0c855c1c9055737", "generation_seconds_batch": 25.566797500941902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 5.728734970092773, "genuineness": 4.6203155517578125, "identity": 0.8283828496932983, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e57e63a46df785611428d3bbaf957397795c9991d7d1e76cc9e37415544137ef.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "e58238993840f7bcf87cc6b87a3693d88f8d215cd3fa37c4b517f2b2a29202b4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "76872a28eed29f11162b3701403a4c97990db799f54b983bde2e2838c709441f", "generation_seconds_batch": 25.20974485890474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.213237762451172, "genuineness": 4.68307638168335, "identity": 0.7844746112823486, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e58238993840f7bcf87cc6b87a3693d88f8d215cd3fa37c4b517f2b2a29202b4.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "e58e80d79bcbeb0b2babe217ac0c6629048afd85d96f3ae5d69d67d1722d002c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dede234f03b5640bc307a1312b2f2d83ea1e7469b3debdc8464db4166609f18f", "generation_seconds_batch": 25.495244815014303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 5.434855937957764, "genuineness": 4.7081804275512695, "identity": 0.8080549836158752, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e58e80d79bcbeb0b2babe217ac0c6629048afd85d96f3ae5d69d67d1722d002c.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "e5ee4b8d8833cc3328c5a0ae9320f506fefbe39686335f00febf5deff18311fb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9c3a87ba00d62a8df044f1bad72dcba9d7f93f9aa33d32607d7d858b92ff71d9", "generation_seconds_batch": 27.97268780192826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.863759994506836, "genuineness": 4.68307638168335, "identity": 0.7280203700065613, "hypothesis": "De deur 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_Jealousy_and_Envy/e5ee4b8d8833cc3328c5a0ae9320f506fefbe39686335f00febf5deff18311fb.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "e6114ed852f4d3b5a0059827f53e41e5184014ceb9dbb65f7ee245e3a372cbd4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0120a0f337e59573b24e2da2b14a2a4a012608a30a85810bea9d12e7a309cdb6", "generation_seconds_batch": 19.678008171962574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.173524379730225, "genuineness": 4.369274139404297, "identity": 0.42194831371307373, "hypothesis": "The 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_Jealousy_and_Envy/e6114ed852f4d3b5a0059827f53e41e5184014ceb9dbb65f7ee245e3a372cbd4.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "e62aa794390016ab0f2dc644e8bd87a2c2bc8de1cefdb2d02d2439ca4d47ab2b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "74f5b5970414cbd305b09af0853f38020edf2e58d95d3c21ca0be1af8beca096", "generation_seconds_batch": 27.220291959005408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.621508598327637, "genuineness": 4.432034492492676, "identity": 0.8048858642578125, "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_Jealousy_and_Envy/e62aa794390016ab0f2dc644e8bd87a2c2bc8de1cefdb2d02d2439ca4d47ab2b.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "e6468d64ec15bf8db13a53f044c6cc4a53c0575fe94bd1e13aeb71269617516d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "16182da4e8c70e932c7a84e554d0c8a3976f487cd63409971480d21317da31e2", "generation_seconds_batch": 24.9499953960767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.12545667588710785, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e6468d64ec15bf8db13a53f044c6cc4a53c0575fe94bd1e13aeb71269617516d.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "e6742b3e27bdaad81bda7550e865d435a079b9640f1be8f2867857f20fcece63", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bcb0dfe921ad4dc3227dce4dc34657ba7f21fc8d53e1e97c5f70feb788ec8d88", "generation_seconds_batch": 22.078744038939476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.418970584869385, "genuineness": 4.632867813110352, "identity": 0.6189814805984497, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que...", "wer": 0.11764705882352941, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e6742b3e27bdaad81bda7550e865d435a079b9640f1be8f2867857f20fcece63.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "e6764d55171093b5f7bac768b7f9ea3c7bf36193fca76eff865e279dbb09f260", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ebfbea57370865889bddddb8b7a0ecf785aba3c6c32b3d79823a5481459c9663", "generation_seconds_batch": 23.90017933899071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 6.141753673553467, "genuineness": 4.469690799713135, "identity": 0.3868909776210785, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e6764d55171093b5f7bac768b7f9ea3c7bf36193fca76eff865e279dbb09f260.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "5697e5f6d6069f77a53f756d0f8da28aa41d917b9fe53ca3508fba05c54ab450", "generation_seconds_batch": 18.96070029598195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.41180419921875, "genuineness": 4.406930446624756, "identity": 0.34903979301452637, "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_Jealousy_and_Envy/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "e70605c38b57c1db5db397448bd8c1a6a6455a78969d97267607eeead6b61c25", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e12a8c0f0f0703d9dede54aa015d8e2053396da03e864a03ac033bdc85b8cb84", "generation_seconds_batch": 27.30863339896314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.7781057953834534, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e70605c38b57c1db5db397448bd8c1a6a6455a78969d97267607eeead6b61c25.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "e71fc692639ff08a9816cfb05156e55baf1859c08928b153d9ac685fbb52dfc9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c9027c0b7fa0a2a1eb3c8b21442f9de99b1ad2c9d1031101dd2a48e1d79d31a", "generation_seconds_batch": 25.643108500982635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.173524379730225, "genuineness": 4.231201171875, "identity": 0.32911431789398193, "hypothesis": "The 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_Jealousy_and_Envy/e71fc692639ff08a9816cfb05156e55baf1859c08928b153d9ac685fbb52dfc9.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "e7a193e002babd17a06ed804256866b3af6f5371cc978911fe54d338f272461d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54be9d91ae5dbfc0e962b3f890f4d27d6c6a4cec803dff6c11ccbbc062d4d234", "generation_seconds_batch": 18.3498158500297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.173524379730225, "genuineness": 4.118232727050781, "identity": 0.3053602874279022, "hypothesis": "The 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_Jealousy_and_Envy/e7a193e002babd17a06ed804256866b3af6f5371cc978911fe54d338f272461d.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "e7ff30a1858af1dad28cc2e148b71d2970600343670aeeb94f9be92350fdad61", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "007984845b6001d5a546b62084e9a01740b7868f5900ad2569576f0745fb6975", "generation_seconds_batch": 25.705223979079165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.49810534715652466, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e7ff30a1858af1dad28cc2e148b71d2970600343670aeeb94f9be92350fdad61.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": "e899d15c910a685becf238f144dc875fe0caea42845e004b194e1a4cfaff054a", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "eef85fd300d1b1c37102c249fdf5c542cfc6ad614a097495dec013f135467e96", "generation_seconds_batch": 19.449114572023973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 5.760505676269531, "genuineness": 4.268857479095459, "identity": 0.767236590385437, "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_Jealousy_and_Envy/e899d15c910a685becf238f144dc875fe0caea42845e004b194e1a4cfaff054a.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "e8b95c4bf9c6d8a0b17af8e512f7b66d27adf06b5c60fe4f2150f6aae539f512", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "83de9437ec833ae6466b06813bb8250a86437869f7a1b593965e46b2de15096f", "generation_seconds_batch": 25.764146773028187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.046441555023193, "genuineness": 4.570107460021973, "identity": 0.7223272323608398, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e8b95c4bf9c6d8a0b17af8e512f7b66d27adf06b5c60fe4f2150f6aae539f512.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "e8bac7c5c27dc0f8ee46af6fc222e7dd7eb7da271473e3040361d7f17c5a123d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "feefd8d3e6414ed2b26dbb8b31516ea6c96d6fa789df745395b4dd8e9468b2a3", "generation_seconds_batch": 25.611332962056622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 5.935244083404541, "genuineness": 4.909013748168945, "identity": 0.7331472635269165, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e8bac7c5c27dc0f8ee46af6fc222e7dd7eb7da271473e3040361d7f17c5a123d.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "e8f6bf7fd2a66e0a38f40c927590b6f61737fbb94cf2e5546c2e2bceba086c45", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bf52f11fb5606340ffcad4d1c6b6598a1f47e9698fb32ad2a60fd6058fc25424", "generation_seconds_batch": 23.97182786196936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.6712087392807007, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e8f6bf7fd2a66e0a38f40c927590b6f61737fbb94cf2e5546c2e2bceba086c45.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "e91120d8ea90f0b66f9fdf5f729cec8e531d53ce4a885b16367e5da513f05cfb", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "84e23871960f06d1fd298ec401428e1e6da7ab194fe7f7e30fd267d0345b8b77", "generation_seconds_batch": 29.085697395028546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.5052895545959473, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e91120d8ea90f0b66f9fdf5f729cec8e531d53ce4a885b16367e5da513f05cfb.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": "e9552095a844309b6bcca44e6705ac010f350afb4a49696c0e9dd6a8ac7cbc33", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9d7713c1ccd2485d85f922e5bf4961c7d5f1cad11379f6ecc048485c92987781", "generation_seconds_batch": 26.10714450397063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.078212261199951, "genuineness": 4.532451152801514, "identity": 0.5896602272987366, "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_Jealousy_and_Envy/e9552095a844309b6bcca44e6705ac010f350afb4a49696c0e9dd6a8ac7cbc33.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "e9a65a4a71950855fc20449b9d2bbdbbde125f5078e456c5f47dfa897a634bea", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4438f2835467ac437fb92fab87e689803a15945e3e934d310a2dd38cecbc0b60", "generation_seconds_batch": 25.178269008989446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 5.919358730316162, "genuineness": 4.68307638168335, "identity": 0.7924729585647583, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e9a65a4a71950855fc20449b9d2bbdbbde125f5078e456c5f47dfa897a634bea.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "d66f407ac65ae0eee8bbe22313cb1b18994413dcbf27406137318623b7669e12", "generation_seconds_batch": 20.640614871983416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.467403411865234, "genuineness": 4.482243061065674, "identity": 0.5975797176361084, "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_Jealousy_and_Envy/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "e9e3d9d20e182d0cbf703bc89901cfe2831ff1e9f096ffa96bee74d420c330b9", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "05efeb0db3208d2cc4651d4be5d15e54b335b2b5355a552ac9352acfa53e8040", "generation_seconds_batch": 17.856223818962462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.057579040527344, "genuineness": 4.218649387359619, "identity": 0.6080814599990845, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e9e3d9d20e182d0cbf703bc89901cfe2831ff1e9f096ffa96bee74d420c330b9.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "e9f09cff04744b65d814baea9b43a0b1cbb10710a03612a595cc74e65dc909fd", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f7d2fa90ff3f541d8d2277b519499e2277f6ec1f10bc0acf5b76240177fd0e5d", "generation_seconds_batch": 25.72707874700427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.09409761428833, "genuineness": 4.607763767242432, "identity": 0.8009765148162842, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/e9f09cff04744b65d814baea9b43a0b1cbb10710a03612a595cc74e65dc909fd.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": "ea584076d422df2052808365d392e4ecc97e661e769dc15700e48bf4a9272cec", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Someone moved the little blue chair.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "c83d6fc769ef84936c0e8b95831e6aea0647ce43f9d4189cfd6d9c6d4abd43b3", "generation_seconds_batch": 19.583416213048622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.229123115539551, "genuineness": 4.65797233581543, "identity": 0.14516055583953857, "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_Jealousy_and_Envy/ea584076d422df2052808365d392e4ecc97e661e769dc15700e48bf4a9272cec.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "ea9c5449bc41f366f51dabf9789fd6110100f29d461b7531d47a84826340b285", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a4069dfcb3e1250a9e19718ec1ad2b9075956712f36b9bb4142ba660c4a7c09b", "generation_seconds_batch": 23.873111734050326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.911416053771973, "genuineness": 4.632867813110352, "identity": 0.6084598898887634, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ea9c5449bc41f366f51dabf9789fd6110100f29d461b7531d47a84826340b285.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "eb3f477f8f4bd17766c746692c0242338e97d633bd9cec108cd56ac85880cd4f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e5a4cdde2d7a5abca1446cc0ce85f7ffa0b913aee23fadea2cdd03e9ce1271b4", "generation_seconds_batch": 31.937278143013828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017013445496559143, "target_z": -0.4433593722578048, "ce": 6.09409761428833, "genuineness": 4.3504462242126465, "identity": 0.16051645576953888, "hypothesis": "The 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_Jealousy_and_Envy/eb3f477f8f4bd17766c746692c0242338e97d633bd9cec108cd56ac85880cd4f.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "ebc2ecf694b411624b7a6e1c60b789430aaa2a9e41e9a1f55f3612cc634cd9f8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "254a5f6bb2bd326d280985921dece90a373e58bdcecaf0871c65fbdbc51b6733", "generation_seconds_batch": 25.19380322797224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03181406855583191, "target_z": -0.4101562502611614, "ce": 6.006728172302246, "genuineness": 4.457139015197754, "identity": 0.6126324534416199, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude. Oude ramen, 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_Jealousy_and_Envy/ebc2ecf694b411624b7a6e1c60b789430aaa2a9e41e9a1f55f3612cc634cd9f8.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "ebd2d3966b7af951b882fdad4ba65cd17507a1ce227384743017eeedc53e3f67", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "09fe479aa6f74e7855522035113ef154027529b2da405d4c32a4df5b690e3b53", "generation_seconds_batch": 23.96776816190686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02310781180858612, "target_z": -0.42968751619200973, "ce": 5.95112943649292, "genuineness": 4.425758361816406, "identity": 0.2541015148162842, "hypothesis": "De deur 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_Jealousy_and_Envy/ebd2d3966b7af951b882fdad4ba65cd17507a1ce227384743017eeedc53e3f67.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "0e56151a1184904ea3f87c3ee1cbbce772b7900a25b9468dac2f5938e09b751f", "generation_seconds_batch": 16.44386429199949, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.213237762451172, "genuineness": 4.632867813110352, "identity": 0.8275163173675537, "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_Jealousy_and_Envy/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.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": "ec16b7a039cf432425d3cc7b1c2ddcfcda23609bfed91542e5b9444a38ff0296", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6e84e78ffabdd8439f49a3d00292ba699dfc844211f23fcd91645c302007add", "generation_seconds_batch": 25.795815675053746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 5.982900142669678, "genuineness": 4.758388519287109, "identity": 0.6278316378593445, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte das Schublade dann neben 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_Jealousy_and_Envy/ec16b7a039cf432425d3cc7b1c2ddcfcda23609bfed91542e5b9444a38ff0296.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "ec1e1706135935fe3fe948674a3a3df7b2a1c62d722e54953a55fda6ab4b8828", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "20b1b9e5ebe5bfa454d677235b85ca95b2f6ddb4a6fef9c68f62fa4aed4f48de", "generation_seconds_batch": 30.53810681705363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 4.95531702041626, "genuineness": 4.15588903427124, "identity": 0.696124792098999, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ec1e1706135935fe3fe948674a3a3df7b2a1c62d722e54953a55fda6ab4b8828.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "ecc411e87ed6e3e96c848e95fe7fac5a2b1ee392e2c2677390e4e2540e75a33a", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bca0388234a70b2f569a27570b0c874f2508fda92d41df2a62fa5d974d1af650", "generation_seconds_batch": 25.38947358704172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 5.967014789581299, "genuineness": 4.494794845581055, "identity": 0.6275829672813416, "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_Jealousy_and_Envy/ecc411e87ed6e3e96c848e95fe7fac5a2b1ee392e2c2677390e4e2540e75a33a.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": "ed47dd5bff01e442f5c12491a4632549e39b029bc6fb8821df39c8d030efe1a4", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "40d4d61b124c5a6b4ec2d017a58b282c82017fb6ce6643f4e0a676135384048c", "generation_seconds_batch": 18.85864643007517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 5.967014789581299, "genuineness": 4.758388519287109, "identity": 0.5824031829833984, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir. Puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ed47dd5bff01e442f5c12491a4632549e39b029bc6fb8821df39c8d030efe1a4.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "ed58ffcff0365f233c6a9c0670d42717cf4db12ee6f89a4aa7893de3574dfd69", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f22956296ffacb1e264281964227d5e1028be927dc8d957cf3a20749e2349aae", "generation_seconds_batch": 18.70319957600441, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 5.839932441711426, "genuineness": 4.3881025314331055, "identity": 0.6743308305740356, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ed58ffcff0365f233c6a9c0670d42717cf4db12ee6f89a4aa7893de3574dfd69.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "ed9a26fc9fe508a70fd0e97ab5ab3fdadd46a9fa047e8f79f43d0e7bd7fb55d5", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4c8a6a3cd91ee0f3a3fc937124d5a5c7ada1f87d8faa0242ea3ce2c538a7fb4e", "generation_seconds_batch": 23.90017933899071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007364049553871155, "target_z": -0.4980468633783156, "ce": 6.006728172302246, "genuineness": 4.432034492492676, "identity": 0.833014965057373, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ed9a26fc9fe508a70fd0e97ab5ab3fdadd46a9fa047e8f79f43d0e7bd7fb55d5.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": "ee794d0d6273218d4d2c3dbd25a2b6ea24c1dfe8631fa57cc5865f0ab1b03dac", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "59c072a4fa824c0d17c82b007e1c65aa74befedc3bca69abe3a9f83c2a3bce0c", "generation_seconds_batch": 19.27059145795647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.2653290033340454, "hypothesis": "De weg gaat linksaf, na de brug. Loop verder, tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ee794d0d6273218d4d2c3dbd25a2b6ea24c1dfe8631fa57cc5865f0ab1b03dac.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": "ee7ac576d3cd81539371f3fd7503b7328061db92490028f2948b4911a4c9c590", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25bc6755092e6a93ba74b2276ebeb7908525c0eecbac01ce9eb97d58ebf232fd", "generation_seconds_batch": 24.914569540997036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.95112943649292, "genuineness": 4.607763767242432, "identity": 0.6282730102539062, "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_Jealousy_and_Envy/ee7ac576d3cd81539371f3fd7503b7328061db92490028f2948b4911a4c9c590.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": "eeb93e931a2841bd2c07256fc3cd2d6d2c898100c26aa91547f2d7d412ecfbd9", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38cd29f482384f33389fb24d4301d466d517d776583233482fa89d670d5c2b6e", "generation_seconds_batch": 25.846327931038104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 5.927301406860352, "genuineness": 4.6956281661987305, "identity": 0.736789882183075, "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_Jealousy_and_Envy/eeb93e931a2841bd2c07256fc3cd2d6d2c898100c26aa91547f2d7d412ecfbd9.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "eed1fc37fc0ca56c7482456352c2d63f4d8a6fb1cf4848bc1858560e59a99ed0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "600cf45b1b5b470574ca51f4a639d39ba503172426c8bf1679cac400bb981b4e", "generation_seconds_batch": 26.353192933951505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 6.09409761428833, "genuineness": 4.607763767242432, "identity": 0.7995253205299377, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/eed1fc37fc0ca56c7482456352c2d63f4d8a6fb1cf4848bc1858560e59a99ed0.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": "ef3326907b0d991aca3eac125ac56f622b85469d45c1a140f5fd44b3a76f4b9f", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The keys are on the kitchen table.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "f603afbbcdf041df5f9087fc157cbfee41e65b40a74f91c7e39c5886af6b7530", "generation_seconds_batch": 18.989632124081254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 6.149696350097656, "genuineness": 4.394378662109375, "identity": 0.31829923391342163, "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_Jealousy_and_Envy/ef3326907b0d991aca3eac125ac56f622b85469d45c1a140f5fd44b3a76f4b9f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "ef5a30a774dce744090911411359d093e885a53283afec9479692485577d4105", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "088ceccd42b221386b7c7c41a4b5a17660f0934d5a6cfd218a310fdd8b5d6d8c", "generation_seconds_batch": 19.611683181021363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 5.831989288330078, "genuineness": 4.65797233581543, "identity": 0.7851312160491943, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ef5a30a774dce744090911411359d093e885a53283afec9479692485577d4105.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "ef980fe32c2d3cd5235571a6e645b1001c74b58c48909417ab6a90c951b5c5e8", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8029f102a6795f248e0716fec322919c802c3c5cccefac1a1da2023f690f6d92", "generation_seconds_batch": 20.390295756049454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 5.665193557739258, "genuineness": 4.319066047668457, "identity": 0.5386024117469788, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ef980fe32c2d3cd5235571a6e645b1001c74b58c48909417ab6a90c951b5c5e8.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "efa0ae1e3d312d316e310cfd0466ef6bb66d5aa855f51a1a447e4b30ea9c5efc", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8d7cc896e59742cea570833a53e258ca996055c99993f1254173f07d9504f10a", "generation_seconds_batch": 25.109759100945666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 5.998785495758057, "genuineness": 4.381826400756836, "identity": 0.4379960596561432, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/efa0ae1e3d312d316e310cfd0466ef6bb66d5aa855f51a1a447e4b30ea9c5efc.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "efe48994ab0782e00d51815af0047ed635029f9a908d9705054378a3e5075976", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f8dfbfdc16b1b9e4273e5222dd8e3e53c3bd29c4964294dc8e07dc7a7f28619e", "generation_seconds_batch": 25.647474114084616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 6.046441555023193, "genuineness": 4.406930446624756, "identity": 0.5497271418571472, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het Oude Raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/efe48994ab0782e00d51815af0047ed635029f9a908d9705054378a3e5075976.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": "f017c7dea89f2d021f8d2191539eeb4b33f9d2c20546c55b34fdd07f715dc829", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5c3c7fc8192aac40f857ec906d234c59ab1a38d22ffd2bd2a2321cf25111cbe", "generation_seconds_batch": 17.040104218991473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 5.919358730316162, "genuineness": 4.632867813110352, "identity": 0.6475492715835571, "hypothesis": "Leur route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f017c7dea89f2d021f8d2191539eeb4b33f9d2c20546c55b34fdd07f715dc829.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "f0737103b5ed5a3850892a3049ce443128c65484b0200a095fa4488c01a18e55", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "864988b66e2d03fe129139277fe22ed461a41227d3e0882e8c07526ab4c05939", "generation_seconds_batch": 18.99186313606333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020495951175689697, "target_z": -0.43554685919973246, "ce": 5.696964263916016, "genuineness": 4.65797233581543, "identity": 0.7842884063720703, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f0737103b5ed5a3850892a3049ce443128c65484b0200a095fa4488c01a18e55.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "f114b44f9d490350b6c2963a17556ef72237dfa25dfccbe15f0e414d01bcda05", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3f8754e81e0d8015b7dbc2f66b91a8739174fdac043ae72c62a33c01815eb05c", "generation_seconds_batch": 25.593534043990076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01788407564163208, "target_z": -0.4414062356361204, "ce": 6.395919322967529, "genuineness": 4.457139015197754, "identity": 0.665743350982666, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f114b44f9d490350b6c2963a17556ef72237dfa25dfccbe15f0e414d01bcda05.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "f15856c6e4cd8b353e54ee6dd38578f7187117b6ef02a9a1dca3b4b63c43677e", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0e4d660d0dc334e907a26a57663eb1fdc652604f52da2ec4be7573abc97226cb", "generation_seconds_batch": 25.59619923797436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.078212261199951, "genuineness": 4.846253395080566, "identity": 0.8503157496452332, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f15856c6e4cd8b353e54ee6dd38578f7187117b6ef02a9a1dca3b4b63c43677e.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "3891814472a2d86c74180abcb64bea75b28fede1764af387ea1d82b488181ab3", "generation_seconds_batch": 23.785890085971914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.221180438995361, "genuineness": 4.406930446624756, "identity": 0.5579127073287964, "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_Jealousy_and_Envy/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-1", "key": "f23b2b1e0a7f8a61f1361b78013bf23a5eac35b69b5b6503fe90813ebb59cefe", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "893958c7ff621a40ea5d1fefb7da5fad6fbe976b44799350e83bed115c75c4e4", "generation_seconds_batch": 19.2082784390077, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02042342722415924, "target_z": -0.5273437455602554, "ce": 6.0146708488464355, "genuineness": 4.344170093536377, "identity": 0.6277127265930176, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f23b2b1e0a7f8a61f1361b78013bf23a5eac35b69b5b6503fe90813ebb59cefe.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "f25c69219f5d089181fa9586585e4da7cc294d2da5488cb743f159259ec8ccf0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "8a7762f8a5749b3ed6debf77d4d3f2312ce2cb47493a19553a20790363279763", "generation_seconds_batch": 26.329743598937057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 4.752779006958008, "genuineness": 4.193545341491699, "identity": 0.7681310176849365, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lindo.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f25c69219f5d089181fa9586585e4da7cc294d2da5488cb743f159259ec8ccf0.mp3" }, { "id": "emo_Jealousy_and_Envy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-nl-0", "key": "f25e5a1936df6147013f4708099287cd162f9e307ff2f7ab381e37baa9fbb0c0", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De deur staat nog open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a63ec6491b71845fd7cb2e1959b765d64d6885800a0a39226d2f6def5eeeedfe", "generation_seconds_batch": 25.890862934058532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03181406855583191, "target_z": -0.4101562502611614, "ce": 5.839932441711426, "genuineness": 4.432034492492676, "identity": 0.46780478954315186, "hypothesis": "De deur 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_Jealousy_and_Envy/f25e5a1936df6147013f4708099287cd162f9e307ff2f7ab381e37baa9fbb0c0.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "f26c855e3947731c9bcba871f53e8f21ea3f8d05e4f8f1f483a9fa863f73556b", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8b258da8a37a13d743390b3f347b682a973458f363991d6ecf42e00e3369c0e2", "generation_seconds_batch": 18.95955078897532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.6485126614570618, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f26c855e3947731c9bcba871f53e8f21ea3f8d05e4f8f1f483a9fa863f73556b.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "f2fe2e460d30016339fec1ca6081048b5a05e6e2fe317e1613f060d8b3ede885", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fab53b52166c8b996499f2fa4e54bb7f4815b21cdc0705303bab0080743e0ffa", "generation_seconds_batch": 18.491391427000053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 6.38797664642334, "genuineness": 4.482243061065674, "identity": 0.3476988971233368, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f2fe2e460d30016339fec1ca6081048b5a05e6e2fe317e1613f060d8b3ede885.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": "f361bca9aa1eed8b232ee995cd677ab31c52d7683afcf2e5d550c7d551f67afe", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "728c208aa75455f49d0a1bba3f12fd6842635c8a997f106265127b3e5b13b455", "generation_seconds_batch": 25.938403517007828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 5.824047088623047, "genuineness": 4.595211505889893, "identity": 0.4807541072368622, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana llévatelas cuando te vaya.", "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_Jealousy_and_Envy/f361bca9aa1eed8b232ee995cd677ab31c52d7683afcf2e5d550c7d551f67afe.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "f3723a31fa809f822e09e1ddf997ad69d5013edf8869d6168aad9d655f70d557", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3c4d126dd97cdb921a4846038572d8d711039a5f9b20bc1111a21f0bf479a116", "generation_seconds_batch": 25.786488558980636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 6.054384231567383, "genuineness": 4.3504462242126465, "identity": 0.3402023911476135, "hypothesis": "The 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_Jealousy_and_Envy/f3723a31fa809f822e09e1ddf997ad69d5013edf8869d6168aad9d655f70d557.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "f37d4ec80e6856265ced7c5badc913eaec4c4d3537866e192cef8bb5227cb96d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "403e636b9280a117574ceddda6f6655f0984a8c56ee164e6de5904c7cc59861f", "generation_seconds_batch": 19.007442898931913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.7952556610107422, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f37d4ec80e6856265ced7c5badc913eaec4c4d3537866e192cef8bb5227cb96d.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "f3d65d1c020221a042ac1902916257d089bdf3c2df97e31e9f9d5ecb43ed528d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fad3ee0555f997dcf80f8a6381b539c67266e4359364eea684024858b55bed64", "generation_seconds_batch": 25.231162413023412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 5.855817794799805, "genuineness": 4.557555198669434, "identity": 0.895378589630127, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f3d65d1c020221a042ac1902916257d089bdf3c2df97e31e9f9d5ecb43ed528d.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "f3df0cc78f995b641403145d756ec0b18f01ee591e8604a59094ebbb4dc4a38d", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5203c882af27fb65571ef9629f87c6cee0989d5ce3fb0517a525241b2c7139f0", "generation_seconds_batch": 27.837132548098452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.054384231567383, "genuineness": 4.457139015197754, "identity": 0.825153112411499, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f3df0cc78f995b641403145d756ec0b18f01ee591e8604a59094ebbb4dc4a38d.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "f42699c52203a025fd89d560d5bc5225feb81513a7a687cac6f63e86c6b84491", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "67fd4c118a040ea6aa0b0b1271c2904c58da450e41b1140d6cca2b645423855a", "generation_seconds_batch": 19.156855802983046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.2767791748046875, "genuineness": 4.18099308013916, "identity": 0.47818922996520996, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f42699c52203a025fd89d560d5bc5225feb81513a7a687cac6f63e86c6b84491.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "f495bdc33293aa7bd5d04616289bdb8f646dfd3c620dd871ceb16a7f824b6015", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ec04c080a39e8b8c125773fbc8c8a361f06daf364305fe4254871c0705459bc8", "generation_seconds_batch": 24.6161754950881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.054384231567383, "genuineness": 4.582659721374512, "identity": 0.512693464756012, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f495bdc33293aa7bd5d04616289bdb8f646dfd3c620dd871ceb16a7f824b6015.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "f4f951ed72d1675d9c81a2c986f77cbe746a00e40a4fa60bedf33c005f173955", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7d82b9603ffacf3363a1ae920798a2b57705da93fbfb4f9259241fcf01578592", "generation_seconds_batch": 20.76800848497078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026590317487716675, "target_z": -0.4218750031339374, "ce": 6.046441555023193, "genuineness": 4.494794845581055, "identity": 0.3080655336380005, "hypothesis": "The 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_Jealousy_and_Envy/f4f951ed72d1675d9c81a2c986f77cbe746a00e40a4fa60bedf33c005f173955.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": "f567539f46b4bcf1a67ef8c61532adce9a5ac4b0b2d7485f7eef544cc6b8e435", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": "75c188bf0a12b559dd5d49bfcc6b0cf93d16468b7e62d2d5c9a70521c4c58c96", "generation_seconds_batch": 18.94835698103998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 5.403085231781006, "genuineness": 4.507347106933594, "identity": 0.7573003768920898, "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_Jealousy_and_Envy/f567539f46b4bcf1a67ef8c61532adce9a5ac4b0b2d7485f7eef544cc6b8e435.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "f5c38c82a18639aca0b038ba275da93840de4bc36088c2550ecbf6b9b13933b8", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9fec03b613c4bd4f90c065ba7c4fc0d1656daa5b02a71d1b78ff87417f61eb63", "generation_seconds_batch": 25.162855291971937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.974957466125488, "genuineness": 4.406930446624756, "identity": 0.7669999599456787, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f5c38c82a18639aca0b038ba275da93840de4bc36088c2550ecbf6b9b13933b8.mp3" }, { "id": "emo_Jealousy_and_Envy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-0", "key": "f65c9b54014fcc2d68374bec150fc1f8afac8327f5274c04376d601ca69b6f62", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Tür ist noch offen.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bb9d55f38028098d832c407b9f07622c538842df694ff319f6f8b0b254391ea1", "generation_seconds_batch": 23.950500419014134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028331562876701355, "target_z": -0.41796876331923377, "ce": 5.8875885009765625, "genuineness": 4.494794845581055, "identity": 0.8093333840370178, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f65c9b54014fcc2d68374bec150fc1f8afac8327f5274c04376d601ca69b6f62.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": "f6c0493584739a82e98df476f161e0c50ca89cc9a526d791dd4ec84ce774fdb3", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb0f51ffe90c92ece6e1c9adcb757b4eed4a5b6ea53beab516544c98e217cde8", "generation_seconds_batch": 26.851088853087276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.229123115539551, "genuineness": 4.821148872375488, "identity": 0.722713828086853, "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_Jealousy_and_Envy/f6c0493584739a82e98df476f161e0c50ca89cc9a526d791dd4ec84ce774fdb3.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "f72e9c11666395316d59c190358f8c8458fb4d772a71dcecae237f38b4378f81", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "67f24463896e2528f06f813e746a12d0fcc61ad07db37b574417f199f900a509", "generation_seconds_batch": 25.736650135018863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 5.927301406860352, "genuineness": 4.808597087860107, "identity": 0.874347984790802, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f72e9c11666395316d59c190358f8c8458fb4d772a71dcecae237f38b4378f81.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "cbd7099eddd6a1feef0f37f82bae1295fc62e2027f1b0266d0137b2784df9656", "generation_seconds_batch": 18.796253976994194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.221180438995361, "genuineness": 4.607763767242432, "identity": 0.8052195310592651, "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_Jealousy_and_Envy/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "heldout-de-2", "language": "de", "sentences": [ "Die Straße führt hinter der Brücke nach links.", "Geh weiter... bis zu dem kleinen Holztor.", "Ich warte auf der anderen Seite." ], "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-2", "key": "f7dd0f293a67f485fb252476beb5f47285cf71cc3441b3c2625d483a7cc970da", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1694661421bc6f0b62773a1f3923a675f9eb845b52bed9596631fac9f3ee76a", "generation_seconds_batch": 24.607758957892656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01962532103061676, "target_z": -0.43749999582141685, "ce": 5.752562999725342, "genuineness": 4.557555198669434, "identity": 0.6975814700126648, "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_Jealousy_and_Envy/f7dd0f293a67f485fb252476beb5f47285cf71cc3441b3c2625d483a7cc970da.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "f7efc05ffac47f71ada9f42f1ac6d73e4d6699f655afda7ed51213ae6f4c5256", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "985cb9e52d00ff0fad250339064278b38118bd6fd9574877dfcf9621b7e872cf", "generation_seconds_batch": 25.022631751024164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.133810997009277, "genuineness": 4.821148872375488, "identity": 0.5997838973999023, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f7efc05ffac47f71ada9f42f1ac6d73e4d6699f655afda7ed51213ae6f4c5256.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "f822a41b3a0864017eab68b5e5c4ad0da72a84b2deab95c54f9e7a1a490d1403", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b686271a3ecff1b45be08b9a994856214890e35d27b670bff0faffa644ab76f7", "generation_seconds_batch": 25.557199361966923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.025719687342643738, "target_z": -0.4238281397556217, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.7636499404907227, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f822a41b3a0864017eab68b5e5c4ad0da72a84b2deab95c54f9e7a1a490d1403.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_Jealousy_and_Envy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": "101e69b2d04514b0e417e7a954a95d5b8147b5a53893e59ae1242a08b770a3b4", "generation_seconds_batch": 18.469482885091566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.300607204437256, "genuineness": 4.457139015197754, "identity": 0.6280181407928467, "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_Jealousy_and_Envy/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.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": "f88dbca3d14c2736eea474680d8ea86a23dfd2903b8c8abbff0b5f46f958f1d6", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "8da043cbeff399a64c1df30b35cf9159c0f00fdcff9b5499396effa55e8eba2d", "generation_seconds_batch": 19.27059145795647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.032684698700904846, "target_z": -0.40820311363947703, "ce": 5.788304805755615, "genuineness": 4.369274139404297, "identity": 0.4426969885826111, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/f88dbca3d14c2736eea474680d8ea86a23dfd2903b8c8abbff0b5f46f958f1d6.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "f8d7b040a7bc62f4e85e315e812aaf2efef7ee53eafc9732da1790f2c8a843e6", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a645c4bb084547387ebe70c211b34e5fdcdd57afaadc73cf7c30d3d48e5c7ed9", "generation_seconds_batch": 19.301650766981766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.12285022437572479, "hypothesis": "The 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_Jealousy_and_Envy/f8d7b040a7bc62f4e85e315e812aaf2efef7ee53eafc9732da1790f2c8a843e6.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "fa2c47a1a30b4a19f0ad11dab8de1d69796d89594db014f99d12a11de19ecea7", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7640efcef9f517fce7e2242a2d24fe120e1c08d4f1bb4b2ffb86a020352eada0", "generation_seconds_batch": 25.11427977506537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.165581703186035, "genuineness": 3.8420867919921875, "identity": 0.2766702175140381, "hypothesis": "The 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_Jealousy_and_Envy/fa2c47a1a30b4a19f0ad11dab8de1d69796d89594db014f99d12a11de19ecea7.mp3" }, { "id": "emo_Jealousy_and_Envy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-0", "key": "fa7b88743d1d2a3f6571671d6ead11765ffd0f2ca26f3e3b8bebe4637a32e61f", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La puerta sigue abierta.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "69ea1dccad51e6078d95944ce7d745219d7ed2b4082d38847e63450aa9e3ae06", "generation_seconds_batch": 25.38947358704172, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024849072098731995, "target_z": -0.42578124294864095, "ce": 5.6254801750183105, "genuineness": 4.337893962860107, "identity": 0.7548201084136963, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/fa7b88743d1d2a3f6571671d6ead11765ffd0f2ca26f3e3b8bebe4637a32e61f.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "fb07bd66d2223b747a863776d8073ff4a70c0991923677119733d550a15b2d75", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b64170c0ae20233d1d81e7e8365bc57dea27c9dc691d3796f4f2722615409129", "generation_seconds_batch": 25.74961236899253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 5.808161735534668, "genuineness": 4.6705241203308105, "identity": 0.803124189376831, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/fb07bd66d2223b747a863776d8073ff4a70c0991923677119733d550a15b2d75.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": "fc3b8a8ed23c7d9b0d02fe65fbacb4174f32d7c3d00228af8d03f31f19400036", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e08145038d3233ac7c1057e6068602c36e0c1ee8612a6444edefa7906e1dd91c", "generation_seconds_batch": 18.902301168069243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 6.078212261199951, "genuineness": 4.796044826507568, "identity": 0.5805569887161255, "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_Jealousy_and_Envy/fc3b8a8ed23c7d9b0d02fe65fbacb4174f32d7c3d00228af8d03f31f19400036.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "fc83969cf5e5cfba5b86366b69e9475a15984355d2f12b66a00f9da06570865c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "409ecb9166d030df6a67b4d0d06b5ba22a552d5d3ca26a052143abdc0c14e206", "generation_seconds_batch": 25.030283520929515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.165581703186035, "genuineness": 4.432034492492676, "identity": 0.6682354211807251, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/fc83969cf5e5cfba5b86366b69e9475a15984355d2f12b66a00f9da06570865c.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "fd1feca20d2ab556a9a4ecf4239a02e9bf234e5b0827fb58df464145860bd1a4", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7a2993a4c3e8c0eef934f797cb464f037eeaf0d4f4609d7a50526f6bcb88fa54", "generation_seconds_batch": 19.20388805202674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.903473377227783, "genuineness": 4.444586753845215, "identity": 0.7157518267631531, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/fd1feca20d2ab556a9a4ecf4239a02e9bf234e5b0827fb58df464145860bd1a4.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-0", "key": "fd2130e033aa2639dcc36631a2d89a8d8afe6f8c70c084079991364920eb39ab", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La porte est encore ouverte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "726db753ca6c217e4dbbf806e9b2555f3f5d63bddb72f44a671c59c3a08f66cd", "generation_seconds_batch": 17.549577704048716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008234679698944092, "target_z": -0.5, "ce": 5.95112943649292, "genuineness": 4.532451152801514, "identity": 0.6356601119041443, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/fd2130e033aa2639dcc36631a2d89a8d8afe6f8c70c084079991364920eb39ab.mp3" }, { "id": "emo_Jealousy_and_Envy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-1", "key": "fd4a626322451658dec4f8595d157a0391d967702b02be90f069d8af7c773d0d", "bucket": "emo_Jealousy_and_Envy", "phase": "wording", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] I found the little box.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] It was beside the old window.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c7af139b96086b32547007d0a1eeb541f540d784c5b3e06c1618688b31a3b125", "generation_seconds_batch": 20.110675685922615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.348263263702393, "genuineness": 4.432034492492676, "identity": 0.4462004601955414, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/fd4a626322451658dec4f8595d157a0391d967702b02be90f069d8af7c773d0d.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "fd8624cec87dac7ca4e51bd2b0d57ec0a5bd3c525a6a1ff165316ef9e8b3ae54", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3aec9ff2504c5df3dcbb61dcec5014eeef4dd0ea91d37ba931933324beb8ea3a", "generation_seconds_batch": 25.699113292968832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00134219229221344, "target_z": -0.4785156308761326, "ce": 5.696964263916016, "genuineness": 4.68307638168335, "identity": 0.728428840637207, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/fd8624cec87dac7ca4e51bd2b0d57ec0a5bd3c525a6a1ff165316ef9e8b3ae54.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": "fdac261e500ba214a7b3f0596510dc087d6971677701534d2fc71bc85b03d602", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a463561c82f400e52b7a2a781dcb536ee294bbb639151fb3563b01c01be76efd", "generation_seconds_batch": 25.530161113012582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011789694428443909, "target_z": -0.4550781251305807, "ce": 5.645336627960205, "genuineness": 4.720732688903809, "identity": 0.6779806613922119, "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_Jealousy_and_Envy/fdac261e500ba214a7b3f0596510dc087d6971677701534d2fc71bc85b03d602.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "fdbfdf818927e8238cadf3fd662c0aafb6cb212bd5dd8a01de4b053debf031b3", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c0eddd8bd1d3ddf52e32365105e2b0e0af896cb120d6723e6c7db9edad5f9153", "generation_seconds_batch": 24.92784259095788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.1894097328186035, "genuineness": 4.909013748168945, "identity": 0.6833182573318481, "hypothesis": "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_Jealousy_and_Envy/fdbfdf818927e8238cadf3fd662c0aafb6cb212bd5dd8a01de4b053debf031b3.mp3" }, { "id": "emo_Jealousy_and_Envy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-de-1", "key": "fe8574f088fdaff9073e75f22ba57be5aa180caf06c04614b75f1633a1271d8c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a63909578e09a22ead3d174212922b221c2fe1159c4ad4ed5ff1f6fd1896ee99", "generation_seconds_batch": 24.286725113983266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.013530939817428589, "target_z": -0.45117188531587715, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.6417860984802246, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie standen neben dem alten Fenster. Wir können gemeinsam hineinschneiden.", "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_Jealousy_and_Envy/fe8574f088fdaff9073e75f22ba57be5aa180caf06c04614b75f1633a1271d8c.mp3" }, { "id": "emo_Jealousy_and_Envy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-es-1", "key": "fec35fe18819b9775b20050dce06d170f77b295267acac1f809108bfdd09caa2", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] He encontrado la cajita.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "13dde3557758528fc16fb32e7d76b2ac8d332b1fa0ad8c7e16537f61b51e6607", "generation_seconds_batch": 24.588115821010433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 5.911416053771973, "genuineness": 4.6956281661987305, "identity": 0.8008174896240234, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/fec35fe18819b9775b20050dce06d170f77b295267acac1f809108bfdd09caa2.mp3" }, { "id": "emo_Jealousy_and_Envy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-fr-1", "key": "ff13b88c0d6edd2c4402fc7a01f8ef2f3c5667b3b53efb0a4e989c2987754326", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cae805fa94ed6d2368afb4b264310fba1be9e02d2cbbee3e3d80eca4a4bf0348", "generation_seconds_batch": 24.107758676982485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.078212261199951, "genuineness": 4.6956281661987305, "identity": 0.7967933416366577, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Jealousy_and_Envy/ff13b88c0d6edd2c4402fc7a01f8ef2f3c5667b3b53efb0a4e989c2987754326.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": "ffa6a7cf9adb6170acb0941d51f41e7ef773e4d70bda5edb36a32470c8d4f82f", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d95c9b1819aa4ec23dd82375b16a8ab0a433eb7b1b92c30682b712e560614bc", "generation_seconds_batch": 23.2767468780512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.935244083404541, "genuineness": 4.7081804275512695, "identity": 0.7902804613113403, "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_Jealousy_and_Envy/ffa6a7cf9adb6170acb0941d51f41e7ef773e4d70bda5edb36a32470c8d4f82f.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": "ffb7212cd03a1df7e75a6099cca13fa5c4c0e38eeb16e235f55504af37202a72", "bucket": "emo_Jealousy_and_Envy", "phase": "heldout", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [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": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2d7e7ad35d10925f65b714d44421af0f5a490baff6a2b71c473f7dbd7dc94bc", "generation_seconds_batch": 25.05561585200485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030943438410758972, "target_z": -0.4121093868828458, "ce": 5.71682071685791, "genuineness": 4.13078498840332, "identity": 0.4425804913043976, "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_Jealousy_and_Envy/ffb7212cd03a1df7e75a6099cca13fa5c4c0e38eeb16e235f55504af37202a72.mp3" }, { "id": "emo_Jealousy_and_Envy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Jealousy_and_Envy-en-0", "key": "ffd807ce84ac2d055924ee2fba3265dfdc2161dd0ec5af69a6a706d304b0840c", "bucket": "emo_Jealousy_and_Envy", "phase": "grid", "candidate": "manual-c1306bd27b08", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a heavy, resonant vocal quality that sounds deliberately slow and weighty, using pauses as weapons to emphasize underlying suspicion and control.\nSCRIPT:\n(Begin with a deep, deliberate breath that forces a slow, measured enunciation of the first phrase.) [3.2 seconds duration] The door is still open.\n(Insert a significant, pregnant pause mid-thought, letting the silence itself communicate the weight of the perceived slight.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude the statement with a low, drawn-out vowel sound that trails off, suggesting unresolved resentment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0c0267fc9490d75854a17d23e7d84efc86be7cddbd1477570d02e56be3c605c", "generation_seconds_batch": 25.643108500982635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014401569962501526, "target_z": -0.44921874869419276, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.4341089427471161, "hypothesis": "The 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_Jealousy_and_Envy/ffd807ce84ac2d055924ee2fba3265dfdc2161dd0ec5af69a6a706d304b0840c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-0-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "781e854baa6ab7fcd8e044467120fe917b137f27939a02ea6bf18cf244610dce", "task_id": "emo_Jealousy_and_Envy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.015272200107574463, "target_z": -0.44726561207250837, "ce": 6.316492557525635, "genuineness": 4.545003414154053, "identity": 0.5023456811904907, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/9b0671a30b29574c5b099773.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-0-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "08819a14c3334b5e883337b67a249dad9cf1dec7a1b0bfe43291c8e675bab485", "task_id": "emo_Jealousy_and_Envy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.165581703186035, "genuineness": 4.519899368286133, "identity": 0.5706857442855835, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/8acbe21b14ad55384e57e90c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-0-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "75a72db1907a828e1c6e9beb34d287abebee5e77a317cc6dd18e90c493927b7c", "task_id": "emo_Jealousy_and_Envy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.03181406855583191, "target_z": -0.4101562502611614, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.5884724855422974, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/1b8f86a93a5329de938a9b71.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-0-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "3b528e2d8dfe8556e1940998bb2c631682ef2d33710aedc19cba41ce545a3ab4", "task_id": "emo_Jealousy_and_Envy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.5022789835929871, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/e8c918c7b4d2ae93d0684f9b.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-0-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "a020bfa58f32b77603e13b7c6a356edbe60dc4f11db6552577998d4cd6cd4eed", "task_id": "emo_Jealousy_and_Envy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.034425944089889526, "target_z": -0.4042968738247735, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.21454700827598572, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/9c5ad150ffd99285da3bca8e.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-0-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 129, "seconds_generated": 10.32, "ended": true, "contract_sha256": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "97c6a651be21d58874b42e3357833f1126f52c07de194b17fc6a6e659a9a22e4", "task_id": "emo_Jealousy_and_Envy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.260893821716309, "genuineness": 4.1998209953308105, "identity": 0.5638221502304077, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/1f25969c0357b490c02d681c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-0-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "55b0ecb889caa5eee2846794787f32a41799ceb9b15b6c4aa13b5ae31d4692e3", "task_id": "emo_Jealousy_and_Envy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.022237196564674377, "target_z": -0.4316406193850289, "ce": 6.268836498260498, "genuineness": 4.20609712600708, "identity": 0.43492475152015686, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/f0db56a840e7670c78cd4a03.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-0-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "8842cd37f2807171a2df63ed0c578ba35db6859b61e4113bed06e2ec01f14cde", "task_id": "emo_Jealousy_and_Envy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.284721851348877, "genuineness": 4.482243061065674, "identity": 0.5943301916122437, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/e11204be5c74487f65e35a21.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-1-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "857827f5a754f9e026614a4b76d86a8485255d3424d6e97b36824fe1d67effcd", "task_id": "emo_Jealousy_and_Envy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.340320587158203, "genuineness": 4.262581825256348, "identity": 0.7330633401870728, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie standen neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/cbabf79d3e6490fe14599ecb.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-1-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "592c30e81deca5f8b4cbc30c262a8dd3490009737a77f37e1917cadd465a8845", "task_id": "emo_Jealousy_and_Envy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.3641486167907715, "genuineness": 4.256305694580078, "identity": 0.4786874055862427, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/f46f4f936c73105fceb58f12.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-1-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "b4e4c65cb1277c057e444ded5f53898d799c5bd4ce4da2328569b5ce76b14ca9", "task_id": "emo_Jealousy_and_Envy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.332377910614014, "genuineness": 4.432034492492676, "identity": 0.6793575286865234, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/8bf304959c26fa3a4b1e993a.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-1-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "9fdfd997f9a081f6f5a183aa5f1326f4fa2241df5721235a3345bcfe13fd865f", "task_id": "emo_Jealousy_and_Envy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.356205940246582, "genuineness": 4.143336772918701, "identity": 0.5540575385093689, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/cb15c38ba2f2af27f157868d.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-1-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "943e8862c6c990b20eb10b7a0aa1105cfd88424ee4a3120972ff24b6066fda79", "task_id": "emo_Jealousy_and_Envy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.38797664642334, "genuineness": 4.168440818786621, "identity": 0.569463849067688, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/170abcb5b175b9c4738d1e59.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-1-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "80625a8c918c4ab8fd95b6c9f3832636d30b39b5294cb05263bbbcf37c6bc8d4", "task_id": "emo_Jealousy_and_Envy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.007436573505401611, "target_z": -0.4648437413816722, "ce": 6.308549880981445, "genuineness": 4.13078498840332, "identity": 0.35620057582855225, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/c7323e50377230a264b37e3e.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-1-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "73b57ab88d2cfe4669a3b8e18d29876dc0e714e44ef4f342330e9b64d5b5588a", "task_id": "emo_Jealousy_and_Envy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.016142815351486206, "target_z": -0.4453125088794892, "ce": 6.435632705688477, "genuineness": 4.545003414154053, "identity": 0.5383509397506714, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/93479ba61d9ef6bfef7e9cb5.mp3" }, { "key": "original-emo_Jealousy_and_Envy-de-1-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "ab2021acabea456463b3a33ff7f575d4377789319361e7112b5ad5b7f9d10df5", "task_id": "emo_Jealousy_and_Envy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.475345611572266, "genuineness": 4.457139015197754, "identity": 0.40958085656166077, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/de/688f08fd4ca83bfe0a9ba923.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-0-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "178d877944151d360ebc1754baab94ab0d09f1d49ff603e561025df049bfd0c8", "task_id": "emo_Jealousy_and_Envy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.316492557525635, "genuineness": 3.9676074981689453, "identity": 0.4552557170391083, "hypothesis": "The 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_Jealousy_and_Envy/en/5edf12790f9ba4f92d05ebaa.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-0-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "3256a13c0e12ccd1609c838fb580f8edaee50c762261171c3978c67881fda5e0", "task_id": "emo_Jealousy_and_Envy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.260893821716309, "genuineness": 4.099404335021973, "identity": 0.5028644800186157, "hypothesis": "The 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_Jealousy_and_Envy/en/a0edbe2f45b9d6e203f5c358.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-0-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "b1fe47cb003d1f67ecf5953a9a73b60ede1e43f5e18577300dcd3326b2923d0c", "task_id": "emo_Jealousy_and_Envy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.004824697971343994, "target_z": -0.47070311781806023, "ce": 6.292664527893066, "genuineness": 4.017816066741943, "identity": 0.3850138485431671, "hypothesis": "The 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_Jealousy_and_Envy/en/63dbf9215da0452576e5495d.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-0-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "19569a60aaa7ac9104be0af649c86fe1f734da596db97e24584ba13b24df6e3e", "task_id": "emo_Jealousy_and_Envy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.181467056274414, "genuineness": 3.9927117824554443, "identity": 0.29661667346954346, "hypothesis": "The 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_Jealousy_and_Envy/en/aa1f7e7ba2222be01fc2112c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-0-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "7bc02d265979b0aff960442cac2f7c134bf076904d65efa7f6d3ba474ac04cae", "task_id": "emo_Jealousy_and_Envy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.002212822437286377, "target_z": -0.4765624942544482, "ce": 6.229123115539551, "genuineness": 3.8797430992126465, "identity": 0.2775561213493347, "hypothesis": "The 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_Jealousy_and_Envy/en/8075c80eace606ffcfc5bc0d.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-0-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "482cf9f9a9410e63b4a1e5226abbcb2c5c8172f9357a582d3965a726ef6b6ec6", "task_id": "emo_Jealousy_and_Envy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.181467056274414, "genuineness": 3.616149425506592, "identity": 0.3418534994125366, "hypothesis": "The 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_Jealousy_and_Envy/en/039e074e056d34bf311c969e.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-0-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "997bc0f7568ace3d0b077ea0fd0bd82521e97a7fe90ef410a19de3d529c58eca", "task_id": "emo_Jealousy_and_Envy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.010919064283370972, "target_z": -0.4570312617522651, "ce": 6.340320587158203, "genuineness": 4.331617832183838, "identity": 0.48187968134880066, "hypothesis": "The 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_Jealousy_and_Envy/en/6dfd37122b76f3ba1fc36def.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-0-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "9da8f78bcfac7c9acbd031a8c71472fe3816fff889f8edc568519af7ea10cc1d", "task_id": "emo_Jealousy_and_Envy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.018754690885543823, "target_z": -0.43945313244310125, "ce": 6.268836498260498, "genuineness": 4.231201171875, "identity": 0.2799953520298004, "hypothesis": "The 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_Jealousy_and_Envy/en/9059ce3fb734c650affc76de.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-1-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "d4d1f3d02fe1a0ade52a2dbbaec3f7194a7ae52f635dfaf5eca26fc2e8370605", "task_id": "emo_Jealousy_and_Envy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 6.41180419921875, "genuineness": 4.2751336097717285, "identity": 0.08725947141647339, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/en/e0d780770a724f727b670723.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-1-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "a10f7aae42d54e2b15ed9f9ddad54f79b492d8c00c3418ce73ac01b50989f4a1", "task_id": "emo_Jealousy_and_Envy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.5740374326705933, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/en/55a3840ece838f242e719407.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-1-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "df5ae413e1bccc0216caea3d2417648b8ddc5f5fd47db5e0620cf367b25fc790", "task_id": "emo_Jealousy_and_Envy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.435632705688477, "genuineness": 4.457139015197754, "identity": 0.3763011693954468, "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/audio/emo_Jealousy_and_Envy/en/20cf1eecbad18109a2c27f3b.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-1-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "15406cda0ddc39bd2cc8fe2a2e3e2962ff6d2598a991fc8b628bacd69ad24349", "task_id": "emo_Jealousy_and_Envy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.005622804164886475, "target_z": -0.49414062356361205, "ce": 6.316492557525635, "genuineness": 4.425758361816406, "identity": 0.3288167715072632, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/en/4c8e41be66af74159dea4aff.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-1-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "899effba7a5c8443cadf621ba3d950f7438401d60b38ca8686a29cce5df8eabe", "task_id": "emo_Jealousy_and_Envy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.38797664642334, "genuineness": 4.281409740447998, "identity": 0.31430208683013916, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/en/69895e982c3e1db1688b329f.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-1-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "3bbbf8bd7187cfd7a42035dc2c547e311f5d858990ab367eef4b14e8d2d0a02f", "task_id": "emo_Jealousy_and_Envy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.01868218183517456, "target_z": -0.5234375057455518, "ce": 6.316492557525635, "genuineness": 4.369274139404297, "identity": 0.404002845287323, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/en/d657cd6a37ca01d2085f69aa.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-1-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "eab3631a62c2880f6aec52c05746a11ab4089db24ea2466de48ebc04d465f940", "task_id": "emo_Jealousy_and_Envy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.2767791748046875, "genuineness": 4.281409740447998, "identity": 0.3386572599411011, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/en/13a68950b273b41a78bcf4c2.mp3" }, { "key": "original-emo_Jealousy_and_Envy-en-1-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "2c49c78d671655d3825cc2d94a312c2541c32309063c90fd467ee63d3281317b", "task_id": "emo_Jealousy_and_Envy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.308549880981445, "genuineness": 4.3881025314331055, "identity": 0.43632304668426514, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/en/2865f4e2c72bce56b64fae54.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-0-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "00d0d934a1187a9f26fe96ff42cbcd2e226a653c2ad4ffb125ea0f5d9db472f1", "task_id": "emo_Jealousy_and_Envy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.927301406860352, "genuineness": 4.250029563903809, "identity": 0.42433691024780273, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/eb1aae1909f9faf4df874073.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-0-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "11f7ec6b30d5a21894ef89a7109f8191e11575c4186fc80e6f9eb1ca4b2c3d7e", "task_id": "emo_Jealousy_and_Envy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.008234679698944092, "target_z": -0.5, "ce": 6.284721851348877, "genuineness": 4.344170093536377, "identity": 0.3693656325340271, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/b7e771a0a9f4cb111649ff83.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-0-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "7cb33de836599e9f73d53c468f2afe47573740b2724d60edd6592cfe34c2d746", "task_id": "emo_Jealousy_and_Envy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.117925643920898, "genuineness": 4.231201171875, "identity": 0.5548834800720215, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/332d72fa7176f7a796d87900.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-0-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "18348d959e57bebe3d9855067d1a41807289aa85b810eb8bead1cf73aa058f8f", "task_id": "emo_Jealousy_and_Envy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.2767791748046875, "genuineness": 4.168440818786621, "identity": 0.38937824964523315, "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_Jealousy_and_Envy/es/4e5b8e2b122f11f980eea533.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-0-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "fc345d5177d7486c6163e42ac49f870539a55da8f7c16aa574d8ccc992232f1e", "task_id": "emo_Jealousy_and_Envy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.062326908111572, "genuineness": 3.9425034523010254, "identity": 0.4113641679286957, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/194962a911d84666b7c78643.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-0-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "586de2db5ea0f34479f0af134867a0216ed3a8c9f4a9a2772b65d1c2a98427d7", "task_id": "emo_Jealousy_and_Envy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.1894097328186035, "genuineness": 4.193545341491699, "identity": 0.5955642461776733, "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_Jealousy_and_Envy/es/5e15426fdca27f646d63af6a.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-0-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "bda02cc27bd48d8ae396c02076797635b7438ba0610aaaa3816de24f718df0a5", "task_id": "emo_Jealousy_and_Envy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.109982967376709, "genuineness": 3.860914945602417, "identity": 0.655765175819397, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/cd348e251600a09adc7748e6.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-0-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "e9e095b30695b9c4d5574a877ad6aa4a50b6aafaafea9da809020b74348f6d3e", "task_id": "emo_Jealousy_and_Envy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.173524379730225, "genuineness": 4.262581825256348, "identity": 0.4690561294555664, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/d0b5fe66ebfa2a569297d22e.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-1-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "201a723a0f6a4a9454800416a0acad8415bc3995e0c6367b8deb795b8fbd1c09", "task_id": "emo_Jealousy_and_Envy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.009177818894386292, "target_z": -0.46093750156696867, "ce": 5.967014789581299, "genuineness": 4.7834930419921875, "identity": 0.47070640325546265, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/9c30be626a8a76e4d6af4258.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-1-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "ea4d468816834920bf0dc10e5a7a83b9da1d829c8e02a7a160cec3aad4c49fe3", "task_id": "emo_Jealousy_and_Envy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.006493434309959412, "target_z": -0.49609376018529644, "ce": 6.284721851348877, "genuineness": 4.557555198669434, "identity": 0.5663774013519287, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/a5a928e12d2ef98822fe65b2.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-1-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "07463108e2403715b33231cd65e640195b77ceea6e06a306fe56e2f93a5a5ed0", "task_id": "emo_Jealousy_and_Envy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 6.1020402908325195, "genuineness": 4.6956281661987305, "identity": 0.5662837028503418, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/b14fc9ea7be3b9e72b157d0c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-1-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "0cac10f15b52e8080dbe4e8acb6423b19da8a8bdc66e9dfbd8b86ac2c8c445b9", "task_id": "emo_Jealousy_and_Envy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.011717185378074646, "target_z": -0.5078125130580723, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.569246768951416, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/f8d26bcceb30ead087a28ab9.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-1-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "f4ff8e00a73dded8eeac9089228d369ba46c0c4d9aa9d3ccb7950a7320fa9c12", "task_id": "emo_Jealousy_and_Envy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 5.982900142669678, "genuineness": 4.6956281661987305, "identity": 0.7184821367263794, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/f7cc73f7c636e209da117874.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-1-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "8b888d0fab01cff4cd06dfb768f71796e2c05275de42f80cf730caa1718f41bf", "task_id": "emo_Jealousy_and_Envy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.221180438995361, "genuineness": 4.21237325668335, "identity": 0.6047452688217163, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/8368f0aba4327e28f17504d4.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-1-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "31a988e0e4e4838f6ba0dc0d66dbf1ad71199afd7c367ac8e7789b0c45cc112f", "task_id": "emo_Jealousy_and_Envy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.007364049553871155, "target_z": -0.4980468633783156, "ce": 6.173524379730225, "genuineness": 4.394378662109375, "identity": 0.6634811758995056, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/da4a2aacf86ddde782e184b1.mp3" }, { "key": "original-emo_Jealousy_and_Envy-es-1-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "b40fac1c3b5e175a6468452241ae9c65c54cf8fd19ed603ab0ca594903100cab", "task_id": "emo_Jealousy_and_Envy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.013458430767059326, "target_z": -0.5117187528727759, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.6513528823852539, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/es/6ccca4db2ed53e117062ce2f.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-0-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "e562a6a794b4137be12ace529988c7619afd72b1a236fe21259f1280032c4dce", "task_id": "emo_Jealousy_and_Envy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.01868218183517456, "target_z": -0.5234375057455518, "ce": 6.181467056274414, "genuineness": 4.519899368286133, "identity": 0.60279780626297, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/d7cb5400ec32d904698427c9.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-0-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "a19a40e4aa3c0a0d09527d4582a820a17ece5a6716509dfa9458b108a864b827", "task_id": "emo_Jealousy_and_Envy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.008234679698944092, "target_z": -0.5, "ce": 6.213237762451172, "genuineness": 4.394378662109375, "identity": 0.8341641426086426, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/af3967fa599c31cb8912c03c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-0-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "d7e663094fe0007980a390ee2ebdb25f34d6824d16d159103b46752d924c2bbd", "task_id": "emo_Jealousy_and_Envy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.01868218183517456, "target_z": -0.5234375057455518, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.8079188466072083, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/b351ee2e697f511e80716181.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-0-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "d7864adf3c68b936d6433eb7f9e22a577045aec6e11d107eb424c591c245aab9", "task_id": "emo_Jealousy_and_Envy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 6.09409761428833, "genuineness": 4.519899368286133, "identity": 0.809813380241394, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/858cb9ecf7aed8427d214900.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-0-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "b6b5888092d5ce54420fe05f16065fe03bc1e6fb7c8395f2b5b0761efc3d5ad5", "task_id": "emo_Jealousy_and_Envy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.015199676156044006, "target_z": -0.5156249926874795, "ce": 6.062326908111572, "genuineness": 4.507347106933594, "identity": 0.8064488768577576, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/44284b68a6932eb0fb5b23b1.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-0-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "1e4be302c51db1d6c386250fe93117400d789f59d13b506abb4577be15b4978d", "task_id": "emo_Jealousy_and_Envy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.1894097328186035, "genuineness": 4.331617832183838, "identity": 0.6476612091064453, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/d116daea0101155b825e80cd.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-0-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "a044cd83e8a1507ce449e3649a1f0d8dc888234092f2787b8bc754c210771e2d", "task_id": "emo_Jealousy_and_Envy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.009975925087928772, "target_z": -0.5039062398147036, "ce": 6.117925643920898, "genuineness": 4.582659721374512, "identity": 0.7646076679229736, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/ab97440e19b1e590e815bfec.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-0-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "cff8113d07f2bd50dcc59421b057c23909598434c356792d21e0ee87ddeb9501", "task_id": "emo_Jealousy_and_Envy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.015199676156044006, "target_z": -0.5156249926874795, "ce": 6.117925643920898, "genuineness": 4.400654315948486, "identity": 0.8339794874191284, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/ee498b441a584ca60290be6c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-1-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "852d56aa44452fc61c1128bedf600276fd2960c6a9da89827983ca68fdd07e67", "task_id": "emo_Jealousy_and_Envy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.012660324573516846, "target_z": -0.4531249885088963, "ce": 6.165581703186035, "genuineness": 4.833701133728027, "identity": 0.7226667404174805, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/8705c2d7cc4169182962f248.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-1-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "8534cb2d7735e647db88457372f3df6d24225df13c9ae396ed5f1fc32a93fe00", "task_id": "emo_Jealousy_and_Envy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.252951145172119, "genuineness": 4.494794845581055, "identity": 0.7554739117622375, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/e6be5c40698a208a56829f40.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-1-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "5f87d6cc7b8bd56a8fb17ae597aee391c55e118f24078fd03fb3fd56098ea8cb", "task_id": "emo_Jealousy_and_Envy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.7392250299453735, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/a285bf0cc245bab6daf4a5cb.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-1-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "d952780a7dd8deb1880dc621c574a174517de33bae956ff79e27403e56484103", "task_id": "emo_Jealousy_and_Envy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0012696832418441772, "target_z": -0.48437500731252053, "ce": 6.157639026641846, "genuineness": 4.457139015197754, "identity": 0.7352190017700195, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/72546bd9508fe2f9937a061e.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-1-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "5ae2e6b2ec9b2509453cf2f08b3159015b0318e351f5c8e743afff797fe054fd", "task_id": "emo_Jealousy_and_Envy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.02136656641960144, "target_z": -0.4335937560067133, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.5946104526519775, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/fd7903723fe124a3b62d30e1.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-1-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "c08230f132171462f65dba40cb30a3a303042a837a6226cc09e96e04b632a65a", "task_id": "emo_Jealousy_and_Envy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 6.300607204437256, "genuineness": 4.68307638168335, "identity": 0.8015627861022949, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/4a3f99d15225c252607282e3.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-1-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "542b8617989112149f2423591ea3f40fad8c73db6b950ceda30bdcb7123aadb3", "task_id": "emo_Jealousy_and_Envy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.0004715770483016968, "target_z": -0.48046873406915175, "ce": 6.213237762451172, "genuineness": 4.595211505889893, "identity": 0.6436418890953064, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/3626509576573f591bb4d875.mp3" }, { "key": "original-emo_Jealousy_and_Envy-fr-1-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "ee468754dd42ee64230f3c48e803f35c8a0a08151e795721f1c47090d536f312", "task_id": "emo_Jealousy_and_Envy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.300607204437256, "genuineness": 4.632867813110352, "identity": 0.6320363879203796, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/fr/1843bad81658727549d0397c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-0-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "c167fefe23f197fd594be4029ec3f3c7f155cd95e8e27f23bb32f91e0ca858a6", "task_id": "emo_Jealousy_and_Envy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.165581703186035, "genuineness": 4.18099308013916, "identity": 0.40775853395462036, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/ded917ff9870c9e76c1b48d1.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-0-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "172da49c5c4f5810ba32f32eddd8a25b9509863fd12ab2caf87cb43015b81fbf", "task_id": "emo_Jealousy_and_Envy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.005695313215255737, "target_z": -0.468750014625041, "ce": 6.173524379730225, "genuineness": 4.193545341491699, "identity": 0.5656483173370361, "hypothesis": "De deur 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_Jealousy_and_Envy/nl/de1387515936e1547f0ef905.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-0-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "253cc38fc26121b1c0517e5a7ddbcb40f5631e60e47ff5196607f124a5108257", "task_id": "emo_Jealousy_and_Envy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.005622804164886475, "target_z": -0.49414062356361205, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.741988480091095, "hypothesis": "De deur 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_Jealousy_and_Envy/nl/3213b503f0c58b5f3159eafb.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-0-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "2361e7838a8899361199a0fb085b7376b871b768defb02c3bfb6991567c5fc09", "task_id": "emo_Jealousy_and_Envy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0021402984857559204, "target_z": -0.4863281105055397, "ce": 6.09409761428833, "genuineness": 4.20609712600708, "identity": 0.7118006944656372, "hypothesis": "De deur 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_Jealousy_and_Envy/nl/ede66cc743a58d131be7e089.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-0-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "2f41be379d199e5d69e10def68d92286b06f97e4972f6edf08bb83d8657d6cf2", "task_id": "emo_Jealousy_and_Envy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.010048449039459229, "target_z": -0.4589843649452843, "ce": 6.038498878479004, "genuineness": 4.20609712600708, "identity": 0.5407164692878723, "hypothesis": "De deur 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_Jealousy_and_Envy/nl/d7331cd86f2eadc7fcee5ee7.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-0-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "431f561c02b915f602c4315ec1bbcbec88f15e1f334ad62abc114e568cdfe63b", "task_id": "emo_Jealousy_and_Envy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.038498878479004, "genuineness": 4.1998209953308105, "identity": 0.7513061761856079, "hypothesis": "De deur 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_Jealousy_and_Envy/nl/4ebb886921c1764360962990.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-0-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "633fe1900a600576697aa16ba37998fc56a7111c57c3b3b76b48a326ddc89781", "task_id": "emo_Jealousy_and_Envy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.003954067826271057, "target_z": -0.47265625443974457, "ce": 6.181467056274414, "genuineness": 4.231201171875, "identity": 0.49104785919189453, "hypothesis": "De deur 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_Jealousy_and_Envy/nl/03f179ddbe426ffbdef32b73.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-0-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "baff1f2ca9c697ff40728da3bfdaabdf3313100a943c10e68ebc5da5c0f0bdda", "task_id": "emo_Jealousy_and_Envy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.006565943360328674, "target_z": -0.4667968780033566, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.7181570529937744, "hypothesis": "De deur 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_Jealousy_and_Envy/nl/e2e7e4baf5aeeb160106cfc5.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-1-seed1701-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "d08bdac34920cb1ed88bab007ab4ddf6923107ce9609f70ff664e1e8d45456d7", "task_id": "emo_Jealousy_and_Envy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.165581703186035, "genuineness": 4.193545341491699, "identity": 0.7345672845840454, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/a8294b3df197afea262b8712.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-1-seed1701-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "7739c7d45902fba31a731c3baf221104836e25f61cf4a15483e8b0f0227ce166", "task_id": "emo_Jealousy_and_Envy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.00039905309677124023, "target_z": -0.48242187069083614, "ce": 5.935244083404541, "genuineness": 4.080576419830322, "identity": 0.6214542388916016, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/b857cc05be69ee2a3b655c06.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-1-seed1701-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "643b1ee9e9bab32e4ccae2acce9bc4709de86e8e0ae6c3173c8912ac19da322d", "task_id": "emo_Jealousy_and_Envy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.00308343768119812, "target_z": -0.47460939106142896, "ce": 6.006728172302246, "genuineness": 4.381826400756836, "identity": 0.6995447278022766, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude eigen. Het kon samen inkijken.", "wer": 0.3333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/f35192f788f05bbd2809a0f1.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-1-seed1701-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "1f966a729e3b0c104a9d918733de254b8c56891d70d3ed3b48e4e1b19035b04e", "task_id": "emo_Jealousy_and_Envy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.7677274942398071, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/1c6b928fab5c4f4b5b8d592c.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-1-seed1702-scale0.0", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "8437efabfd64deb65728bd84571d995941469e909cad673bd25ce7f71bd5b35f", "task_id": "emo_Jealousy_and_Envy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": 0.008307188749313354, "target_z": -0.46289063818865306, "ce": 6.205295085906982, "genuineness": 4.306513786315918, "identity": 0.5319439172744751, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/cbf463f25ea41f043889c252.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-1-seed1702-scale0.5", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "de349ed07db476b1c3e8a88ec1319491a388ec37e3700dcb9f1aea8553794087", "task_id": "emo_Jealousy_and_Envy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.008234679698944092, "target_z": -0.5, "ce": 6.046441555023193, "genuineness": 4.3127899169921875, "identity": 0.7503892779350281, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/2fed3fedd3c52329479603b9.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-1-seed1702-scale0.75", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "b0496ca6d3ecf639257f9788c375d35c9c4453ac8eed49a05a54fef08d03a410", "task_id": "emo_Jealousy_and_Envy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.004752174019813538, "target_z": -0.49218748694192765, "ce": 6.054384231567383, "genuineness": 4.557555198669434, "identity": 0.5763759613037109, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/269bd8f2f332716b1767d215.mp3" }, { "key": "original-emo_Jealousy_and_Envy-nl-1-seed1702-scale1.0", "bucket": "emo_Jealousy_and_Envy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "7b37b1085c97c5b829f6483b96bdca99bafc8836a0fbc94f9b8bd71d6ef9a249", "mp3_sha256": "01b44fb053cb77fa8af7fcb0c65f43d61543b43a420d398288428f9a6b4b3cfc", "task_id": "emo_Jealousy_and_Envy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Jealousy and Envy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Jealousy and Envy. 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 Jealousy and Envy. 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 Jealousy and Envy. 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": -0.0030109286308288574, "target_z": -0.4882812471272241, "ce": 6.125868320465088, "genuineness": 4.250029563903809, "identity": 0.6978762745857239, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Jealousy_and_Envy/nl/545bd10f19bdc0dfd0b952e0.mp3" } ], "source_standard_audio_unchanged": true }