{ "complete": true, "report": { "bucket": "emo_Elation", "label": "Intense Elation", "definition": { "id": "emo_Elation", "category": "emotion", "head": "emo_Elation", "pole": "high", "label": "Intense Elation", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_elation/full-v2-sealed/sealed-selected", "mission": "emotion_elation", "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": 6.33650803565979, "genuineness": 4.07794047832489, "wer": 0.005151990700377797, "identity": 0.614624768793583, "voiceclap": 0.05607702881097794, "fitness": 0.622437342819331, "steering_v2": 0.5945381595669132, "raw_target": 0.6889947687089443, "target_cdf": 0.5945381595669132, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.323323211669922, "genuineness": 4.050702452659607, "wer": 0.003268817204301075, "identity": 0.614624768793583, "fitness": 0.6189179711092582, "steering_v2": 0.5880538328839282 }, "none": { "n": 50, "ce": 6.349692859649658, "genuineness": 4.105178503990174, "wer": 0.007035164196454519, "identity": null, "fitness": 0.6259567145294038, "steering_v2": 0.6010224862498983 } } } } ], "selected_wording": { "id": "manual-a8a332cdd043", "general": "Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.", "inline": [ "Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.", "Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.", "Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak." ], "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": 1.0 }, "n": 20, "target_z": -0.018554686333350813, "target_raw": 0.43864246681332586, "ce": 6.207280707359314, "genuineness": 4.171265113353729, "identity": 0.5454502448439598, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.033917758613824844, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.3311035103426718, "target_raw": 1.4083173632621766, "ce": 6.102437496185303, "genuineness": 3.9627437233924865, "identity": 0.5613134935498237, "wer": 0.0058823529411764705, "valid_fraction": 1, "identity_delta": -0.01805450990796089, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.018554686333350813, "target_raw": 0.43864246681332586, "ce": 6.207280707359314, "genuineness": 4.171265113353729, "identity": 0.5454502448439598, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.033917758613824844, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 2.826953084815417, "target_raw": 2.4830248594284057, "ce": 5.684950828552246, "genuineness": 3.858404541015625, "identity": 0.4190895356237888, "wer": 0.014353070175438597, "valid_fraction": 1, "identity_delta": -0.16027846783399582, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 2.1739257660187468, "target_raw": 2.0138511091470717, "ce": 5.9022821426391605, "genuineness": 3.9002971172332765, "identity": 0.4340350978076458, "wer": 0.009399509803921569, "valid_fraction": 1, "identity_delta": -0.14533290565013884, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 1.6770019575647483, "target_raw": 1.6568314254283905, "ce": 6.030357718467712, "genuineness": 3.9676077008247375, "identity": 0.5137707948684692, "wer": 0.006458333333333333, "valid_fraction": 1, "identity_delta": -0.06559720858931542, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.4153319978708705, "target_raw": 1.468832129240036, "ce": 6.0931047916412355, "genuineness": 4.039154517650604, "identity": 0.5122769862413407, "wer": 0.01215686274509804, "valid_fraction": 0.95, "identity_delta": -0.06709101721644402, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 0.8877929668703985, "target_raw": 1.0898166447877884, "ce": 6.146519255638123, "genuineness": 4.1194878101348875, "identity": 0.4949357107281685, "wer": 0.012222222222222221, "valid_fraction": 1, "identity_delta": -0.08443229272961617, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 0.647717304122401, "target_raw": 0.9173319786787033, "ce": 6.160816121101379, "genuineness": 4.189151906967163, "identity": 0.5196998983621597, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.059668105095624924, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 0.3908203188517567, "target_raw": 0.7327618718147277, "ce": 6.203309392929077, "genuineness": 4.198565948009491, "identity": 0.5115237414836884, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.06784426197409629, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.3311035103426718, "target_raw": 1.4083173632621766, "ce": 6.102437496185303, "genuineness": 3.9627437233924865, "identity": 0.5613134935498237, "wer": 0.0058823529411764705, "valid_fraction": 1, "identity_delta": -0.01805450990796089, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 0.5924804668703986, "target_raw": 0.8776465423405171, "ce": 6.161213231086731, "genuineness": 4.189465749263763, "identity": 0.543022383749485, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03634561970829964, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 0.4093750031110645, "target_raw": 0.7460926629602909, "ce": 6.178687119483948, "genuineness": 4.230730664730072, "identity": 0.5624932929873466, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.016874710470438002, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 0.38625488976378475, "target_raw": 0.7294817954301834, "ce": 6.1854383707046505, "genuineness": 4.224611473083496, "identity": 0.5416808262467384, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03768717721104622, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 0.3666748235321251, "target_raw": 0.7154143087565898, "ce": 6.170347332954407, "genuineness": 4.208293819427491, "identity": 0.5463703624904156, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.03299764096736908, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.12336425828240037, "target_raw": 0.5406054958701134, "ce": 6.188615489006042, "genuineness": 4.222101104259491, "identity": 0.5616274312138557, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.017740572243928908, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.11088867287961457, "target_raw": 0.5316422916948795, "ce": 6.2243575096130375, "genuineness": 4.28266487121582, "identity": 0.5327599830925465, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.04660802036523819, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 2.9152343104454115, "target_raw": 2.5464513540267943, "ce": 5.638585448265076, "genuineness": 3.8431851625442506, "identity": 0.42049329802393914, "wer": 0.024763931888544893, "valid_fraction": 0.95, "identity_delta": -0.15887470543384552, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 2.781640558889879, "target_raw": 2.4504696398973467, "ce": 5.735833525657654, "genuineness": 3.833457326889038, "identity": 0.42655174136161805, "wer": 0.05821787925696594, "valid_fraction": 0.9, "identity_delta": -0.1528162620961666, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 2.4884765507038806, "target_raw": 2.2398431420326235, "ce": 5.834968042373657, "genuineness": 3.8704859375953675, "identity": 0.41612362693995236, "wer": 0.015054824561403508, "valid_fraction": 1, "identity_delta": -0.16324437651783227, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 2.3734374574821184, "target_raw": 2.157192200422287, "ce": 5.786815547943116, "genuineness": 3.8566786646842957, "identity": 0.3850165815092623, "wer": 0.036119281045751635, "valid_fraction": 0.95, "identity_delta": -0.19435142194852234, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 2.3513671220380177, "target_raw": 2.141335555911064, "ce": 5.650747656822205, "genuineness": 3.834084928035736, "identity": 0.36824854779988525, "wer": 0.03855972652218782, "valid_fraction": 0.95, "identity_delta": -0.21111945565789939, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.1919921199639747, "target_raw": 2.0268310546875, "ce": 5.880241203308105, "genuineness": 3.8952762722969054, "identity": 0.4736874982714653, "wer": 0.020957602339181286, "valid_fraction": 1, "identity_delta": -0.10568050518631936, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 1.7667968737037232, "target_raw": 1.7213454455137254, "ce": 6.003154039382935, "genuineness": 3.984709846973419, "identity": 0.45797003582119944, "wer": 0.005902777777777778, "valid_fraction": 1, "identity_delta": -0.12139796763658524, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 1.7130615056623033, "target_raw": 1.6827387541532517, "ce": 6.051505064964294, "genuineness": 3.9845529913902284, "identity": 0.49682899117469786, "wer": 0.009399509803921569, "valid_fraction": 1, "identity_delta": -0.08253901228308677, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 1.6815429544261404, "target_raw": 1.6600939482450485, "ce": 6.025989246368408, "genuineness": 4.012638294696808, "identity": 0.5071335837244988, "wer": 0.020976307189542485, "valid_fraction": 0.95, "identity_delta": -0.0722344197332859, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.4548584001064564, "target_raw": 1.4972302526235581, "ce": 6.082183623313904, "genuineness": 4.02158156633377, "identity": 0.525651766359806, "wer": 0.020772058823529414, "valid_fraction": 0.9, "identity_delta": -0.05371623709797859, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.2347656065928683, "target_raw": 1.3391024708747863, "ce": 6.113358640670777, "genuineness": 4.051706624031067, "identity": 0.4315834756940603, "wer": 0.009089912280701754, "valid_fraction": 1, "identity_delta": -0.14778452776372433, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 0.8728759673751376, "target_raw": 1.0790993832051754, "ce": 6.137980914115905, "genuineness": 4.148357629776001, "identity": 0.49829026460647585, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": -0.08107773885130883, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 0.8127685740506359, "target_raw": 1.0359146490693092, "ce": 6.1782899618148805, "genuineness": 4.1232534646987915, "identity": 0.46026393324136733, "wer": 0.013157894736842105, "valid_fraction": 0.95, "identity_delta": -0.11910407021641731, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 0.7669189518749017, "target_raw": 1.002973547577858, "ce": 6.1350024223327635, "genuineness": 4.1097599267959595, "identity": 0.4915436327457428, "wer": 0.025087719298245614, "valid_fraction": 0.95, "identity_delta": -0.08782437071204185, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.5493896381807092, "target_raw": 0.8466875225305557, "ce": 6.153667640686035, "genuineness": 4.13360892534256, "identity": 0.5175580464303493, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0618099570274353, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 0.5325195517959885, "target_raw": 0.8345670469105244, "ce": 6.168560194969177, "genuineness": 4.143336808681488, "identity": 0.5093418844044209, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.0700261190533638, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 0.21730956261585604, "target_raw": 0.6081014022231102, "ce": 6.190402555465698, "genuineness": 4.28266487121582, "identity": 0.49180653914809225, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.08756146430969239, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.3495117225740168, "target_raw": 0.20086320489645004, "ce": 6.204103684425354, "genuineness": 4.341659641265869, "identity": 0.5793680034577846, "wer": 0.008333333333333333, "valid_fraction": 0.95, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": -0.39677734368518613, "target_raw": 0.16690476536750792, "ce": 6.189012575149536, "genuineness": 4.3573497295379635, "identity": 0.5819085136055946, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0025405101478099823, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.2984374968889355, "target_raw": 0.23755797296762465, "ce": 6.175112915039063, "genuineness": 4.332873153686523, "identity": 0.5792529836297036, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.00011501982808113099, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.39848633126847144, "target_raw": 0.16567692682147026, "ce": 6.188615441322327, "genuineness": 4.316555547714233, "identity": 0.5494333744049072, "wer": 0.008333333333333333, "valid_fraction": 0.95, "identity_delta": -0.029934629052877425, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.4042480482425721, "target_raw": 0.1615373659133911, "ce": 6.260099515914917, "genuineness": 4.392872085571289, "identity": 0.5759987241029739, "wer": 0.005714285714285714, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": -0.10560547205550604, "target_raw": 0.3760999935865402, "ce": 6.278049974441529, "genuineness": 4.297601857185364, "identity": 0.5770276230573654, "wer": 0.008492941840767928, "valid_fraction": 1, "identity_delta": 0.0010288989543914796, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 0.8689257689224069, "target_raw": 1.0762613251805306, "ce": 6.20569221496582, "genuineness": 4.126391482353211, "identity": 0.5354003190994263, "wer": 0.022891329113297075, "valid_fraction": 0.98, "identity_delta": -0.040598405003547666, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 1.0239257768037704, "target_raw": 1.1876225697994232, "ce": 6.217209081649781, "genuineness": 4.145407881736755, "identity": 0.5207838375866413, "wer": 0.033813288161114244, "valid_fraction": 0.96, "identity_delta": -0.05521488651633263, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.15500000788136342, "ci95_z": [ -0.3934374861039119, 0.062265604104016714 ], "language_deltas": { "en": 0.002929679074200281, "de": -0.11328127540702683, "fr": 0.20937496888935492, "nl": -0.32597656314813844, "es": -0.548046848815207 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.01151686668395996, "delta_genuineness": -0.01901639938354492, "delta_wer": -0.01092195904781717, "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": 0.9745312409779129, "ci95_z": [ 0.8117285086834374, 1.0920410059871812 ], "language_deltas": { "en": 1.0597167877686549, "de": 0.6713867101297587, "fr": 1.0101562152597796, "nl": 1.1466308664721159, "es": 0.9847656252592554 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.07235775947570801, "delta_genuineness": -0.17121037483215332, "delta_wer": 0.014398387272529149, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.2986425761870661, "ci95_z": [ 0.22462890517409018, 0.372656247200042 ], "language_deltas": { "en": 0.22250976915735446, "de": 0.3880859337407971, "fr": 0.39965819771304406, "nl": 0.1951660072316072, "es": 0.28779297309252755 }, "languages_improved": 5, "clear_gain": true, "delta_ce": 0.017950458526611326, "delta_genuineness": -0.09527022838592529, "delta_wer": 0.0027786561264822136, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 1.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793024899.2470107, "example": { "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "sentences": [ "Je bericht kwam nadat ik vertrokken was.", "Ik las het twee keer... en legde mijn telefoon weg.", "Zeg maar wanneer we kunnen praten." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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.", "language": "nl", "seed": 1701, "scale": 0.0, "cfg": 1.0, "frames": 128, "reference": true } }, "rows": [ { "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": "000c672a7c9e5e0c4a0f41b11b46eefe9a744d6de93edcda3c9559a78a2d1d66", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I wrote the number on the envelope.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a83c8403f1b0beb8637f89ebf19ad1f103244a1a37192d526e229b4475121c77", "generation_seconds_batch": 23.022909080027603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6755998134613037, "target_z": 1.703125051851075, "ce": 6.23706579208374, "genuineness": 3.7040140628814697, "identity": 0.37335166335105896, "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_Elation/000c672a7c9e5e0c4a0f41b11b46eefe9a744d6de93edcda3c9559a78a2d1d66.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "000e4b01315db9ccfecc8e6f4b4e604ebf06d21078090488e5dd8c4f50574f9a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8e80c305c35db8207adc8b37aa8b26f856be8cf65b3dd9dd5342f644a1fc895e", "generation_seconds_batch": 16.39090766396839, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.247230052947998, "target_z": 3.8906248444467746, "ce": 5.708878040313721, "genuineness": 3.452972412109375, "identity": 0.27423033118247986, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/000e4b01315db9ccfecc8e6f4b4e604ebf06d21078090488e5dd8c4f50574f9a.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "007179df56dd5df792506a46bfd6a28db39cdbc0c548342a371b12065f9e1d4d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3f30954b9b3f8830eeec7ef6113bcbf2f3bcd6671fd6a7e84d188416a0079a33", "generation_seconds_batch": 24.343300836044364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7971706390380859, "target_z": 0.48046873703723125, "ce": 5.959072113037109, "genuineness": 3.7291181087493896, "identity": 0.10117294639348984, "hypothesis": "Ik 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_Elation/007179df56dd5df792506a46bfd6a28db39cdbc0c548342a371b12065f9e1d4d.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "00fae98a9027e19678ae8790ee8ab9fc5d3db115dab9402ca84bb6515e185469", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4f8e8b1a04bc48d3e43047e86bc0ead5e5cdf5fcee4533b536b1685ddcc6161d", "generation_seconds_batch": 24.089942379039712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3482635021209717, "target_z": 4.03124993777871, "ce": 5.8875885009765625, "genuineness": 4.042920112609863, "identity": 0.4497855007648468, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que ha identidad.", "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_Elation/00fae98a9027e19678ae8790ee8ab9fc5d3db115dab9402ca84bb6515e185469.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "019236166477dcbd43e321723941c1c94dd23abd40858c03b97bce3736fe1e3d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "89926bd47b5f85becf7cce04227bb739334e3f12604df79b8d261bbd8e19972f", "generation_seconds_batch": 24.11119312106166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9936244487762451, "target_z": 0.7539062525925537, "ce": 6.38003396987915, "genuineness": 4.105680465698242, "identity": 0.46415793895721436, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/019236166477dcbd43e321723941c1c94dd23abd40858c03b97bce3736fe1e3d.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "019eba9748593825ca41d6876403eaa167cdf5091ea41b9daca77c616a532bb8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "661da793e96d0f09e9eff767d39eb3fdeec0c699d0c51e4e50a6f231efb50409", "generation_seconds_batch": 16.998837611055933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6868257522583008, "target_z": 1.7187500622212901, "ce": 5.474569320678711, "genuineness": 3.7416701316833496, "identity": 0.15654510259628296, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/019eba9748593825ca41d6876403eaa167cdf5091ea41b9daca77c616a532bb8.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "c57cc8a8292a6f517d67c9d6b2f166588b8a73b0b12850209fc177b098613b87", "generation_seconds_batch": 16.586406468064524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40671873092651367, "target_z": -0.0629882712038542, "ce": 5.990842819213867, "genuineness": 4.65797233581543, "identity": 0.7450105547904968, "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_Elation/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "02324dd9685ddc340a208084bec69f308c0a90877fc1e309dbb55c7c48a880a5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aa26edfbf0cad76adf9368cc5b0d30970c3b49c6c9f0afda94a90d4ec9bc662d", "generation_seconds_batch": 25.382392905070446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6924386024475098, "target_z": 1.7265624014829573, "ce": 5.7684478759765625, "genuineness": 4.074300289154053, "identity": 0.6218531131744385, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/02324dd9685ddc340a208084bec69f308c0a90877fc1e309dbb55c7c48a880a5.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "026d38472fe5b60f2712dc460e361fe5caefac13dbafd10d974cbba7f9ccefec", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dd580f70471a704055456d33735d36b0e9fbb49482fed79352018263c886d98c", "generation_seconds_batch": 25.056692978017963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9795920252799988, "target_z": 0.734374989629785, "ce": 4.961274147033691, "genuineness": 3.2615532875061035, "identity": 0.6407520771026611, "hypothesis": "The 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_Elation/026d38472fe5b60f2712dc460e361fe5caefac13dbafd10d974cbba7f9ccefec.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "026ef11d0e5f05e288eae360154cdb14ee48a4166705cd3797e6d8806a8b0a2c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "838472ad782ed873232d3b1549025240784098f8f0c8b17191e93c5a3c6ac710", "generation_seconds_batch": 22.44510543998331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8336549401283264, "target_z": 0.53125002074043, "ce": 6.038498878479004, "genuineness": 4.042920112609863, "identity": 0.6117972135543823, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/026ef11d0e5f05e288eae360154cdb14ee48a4166705cd3797e6d8806a8b0a2c.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "02729e90b8a874a81904771ffa3809ba4a09147cd1c7bdc987e6e1346034aabf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2f0702cdb2ab6b7d5723c870e8e373c25eb137218e3b3488bb95e53c2fc00639", "generation_seconds_batch": 22.474981648963876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5137158632278442, "target_z": 0.08593747407446246, "ce": 6.324435234069824, "genuineness": 4.369274139404297, "identity": 0.5372551083564758, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/02729e90b8a874a81904771ffa3809ba4a09147cd1c7bdc987e6e1346034aabf.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "02d510caf32c90560fcb9d5c175f5d979568b2cc36e46e286f2f92f2806e8ff6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "af518d181c417df75cfaaf04ffaa223ff39c8ddf5ccdd752635cd798689edb7b", "generation_seconds_batch": 21.99179253494367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9459142684936523, "target_z": 0.6875000414808601, "ce": 6.0305562019348145, "genuineness": 4.2249250411987305, "identity": 0.5080603361129761, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/02d510caf32c90560fcb9d5c175f5d979568b2cc36e46e286f2f92f2806e8ff6.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "0314c76516bcd008e7b753f02ad08f5dcdfc92b897a5cbac26b1aab0a569582f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2bae9b478f6890077964b4808310d9d0dfa85100936de505d363a48b168e39bb", "generation_seconds_batch": 22.735171312000602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06467863917350769, "target_z": -0.5390624844446775, "ce": 6.24500846862793, "genuineness": 4.557555198669434, "identity": 0.5928668975830078, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0314c76516bcd008e7b753f02ad08f5dcdfc92b897a5cbac26b1aab0a569582f.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": "03b5cfcea41a7a967bd794482597ff0d6fac807847b342fed12711fb4bb9e700", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "001d63510458f8b5be8cda274f65eafd3124638efde300341f44b78a5dbeadf0", "generation_seconds_batch": 23.592388552962802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9262688159942627, "target_z": 0.6601561903712636, "ce": 6.356205940246582, "genuineness": 3.8797430992126465, "identity": 0.47906196117401123, "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_Elation/03b5cfcea41a7a967bd794482597ff0d6fac807847b342fed12711fb4bb9e700.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "044636c64d95aa1e030e60e492e200e06384fbb2fe45de6fa9582bc0db5b3830", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "723194b9aa31d82bf9bf3107f4d0677d7283f45a4a3bb940c3f68025337f40d9", "generation_seconds_batch": 22.649113182909787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5015978813171387, "target_z": 1.4609375570361827, "ce": 5.903473377227783, "genuineness": 4.137060642242432, "identity": 0.6639251708984375, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/044636c64d95aa1e030e60e492e200e06384fbb2fe45de6fa9582bc0db5b3830.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "04e9f9918149f7e3f28dd1f41abe97b44fee91232bccc0d7bda3aff1d34cc405", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4452f3736ea65f43ee5bbeb051b4c5f6e16d120e3fb5601877f16b2e12c32e6f", "generation_seconds_batch": 16.68467323400546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.287092387676239, "target_z": -0.22949219462952283, "ce": 6.268836498260498, "genuineness": 4.300237655639648, "identity": 0.5285682082176208, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/04e9f9918149f7e3f28dd1f41abe97b44fee91232bccc0d7bda3aff1d34cc405.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "050b563aa062f5a6a93d56a3802b823bea4fad8a420005a55e70de5242837abf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7d68329b4067259dadd3f4040a8530cddbf6fb02254c96db38c05c8ac1aabbcc", "generation_seconds_batch": 23.64345809200313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22324490547180176, "target_z": -0.31835937888883065, "ce": 6.205295085906982, "genuineness": 4.369274139404297, "identity": 0.5971970558166504, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/050b563aa062f5a6a93d56a3802b823bea4fad8a420005a55e70de5242837abf.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "0510bd16b0482e185bea71d7b1bd88ee9c840af976d7a4752f2451d207ab088e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6b32d2f8dcdcb62e4117ec34a780aa1a554243379d7016a3bdb55e1d85a548ed", "generation_seconds_batch": 23.36523894604761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8206446170806885, "target_z": 3.2968747822254847, "ce": 5.808161735534668, "genuineness": 3.9048471450805664, "identity": 0.45406144857406616, "hypothesis": "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_Elation/0510bd16b0482e185bea71d7b1bd88ee9c840af976d7a4752f2451d207ab088e.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "cd45268ca52f35eff7243a32d276404f117d5c81b78888d53b4fcb84811b1569", "generation_seconds_batch": 17.122808127081953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15308284759521484, "target_z": -0.41601561074095433, "ce": 6.316492557525635, "genuineness": 4.632867813110352, "identity": 0.6670109629631042, "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_Elation/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "060c22c9a8a8546c739f42607aed33cc5594c0a4ede7576f38b9d661f9c6ed7a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "632f339c705ec29d24223ca4d3000a680ba9a5a71efcc59404525be63805259d", "generation_seconds_batch": 21.300581544986926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24710001051425934, "target_z": -0.2851562525925537, "ce": 6.181467056274414, "genuineness": 4.394378662109375, "identity": 0.6296213865280151, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/060c22c9a8a8546c739f42607aed33cc5594c0a4ede7576f38b9d661f9c6ed7a.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": "06bbb5f0085701d94459f5950d84710c0147dc4e5971701b584c19f5fbdf81dd", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b4eccfcd91de64195576e3c120240f9cb883a36e68451e90baf1fce5ef7c09d0", "generation_seconds_batch": 15.128525372943841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.876774311065674, "target_z": 3.3749998340765597, "ce": 6.205295085906982, "genuineness": 4.055472373962402, "identity": 0.6900134086608887, "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_Elation/06bbb5f0085701d94459f5950d84710c0147dc4e5971701b584c19f5fbdf81dd.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "078802e43cef92221b9e937e28edecdf68f08d30c6ce897df9a025e6ff774e1e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "56ac86c913ddca3392d4b394e3a3ddd8a7ada8f14c4e27015528ea416a3b45dd", "generation_seconds_batch": 16.976909947930835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6868257522583008, "target_z": 1.7187500622212901, "ce": 6.1020402908325195, "genuineness": 3.9550557136535645, "identity": 0.4894079566001892, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/078802e43cef92221b9e937e28edecdf68f08d30c6ce897df9a025e6ff774e1e.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "08183ac83fb683ee9e2e52c4e369606e4c2fab03ef6ef46aa608791475272a05", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "485d2acbf533b821104c241019bbc5fd9b440c2252f132dccf71cf55ce73d68f", "generation_seconds_batch": 17.496147500933148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5072107315063477, "target_z": 1.4687498962978498, "ce": 6.006728172302246, "genuineness": 4.017816066741943, "identity": 0.7263627052307129, "hypothesis": "De deur 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_Elation/08183ac83fb683ee9e2e52c4e369606e4c2fab03ef6ef46aa608791475272a05.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": "087fb5352a19606a310af8f0fd22396cd643b62355846a6e256de93360a3d9fa", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96015c867c17a4fefdb020d91661d3418eeeaaf2fa51f54202b2e355cd8246f2", "generation_seconds_batch": 21.28363686101511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5965071320533752, "target_z": 0.20117188407393813, "ce": 6.3641486167907715, "genuineness": 4.218649387359619, "identity": 0.4912090003490448, "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_Elation/087fb5352a19606a310af8f0fd22396cd643b62355846a6e256de93360a3d9fa.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "089be6b9ea299bfbb28b47cf44687fc993edebc8da7f5b6b1a5b2d789e7c288d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c9fae35de6e1ce3359fb37c261800ca3f7eafb32fa82c35d777bec07627ccff8", "generation_seconds_batch": 16.228698365972377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8094186782836914, "target_z": 3.28124977185527, "ce": 6.09409761428833, "genuineness": 4.061748504638672, "identity": 0.4892862141132355, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/089be6b9ea299bfbb28b47cf44687fc993edebc8da7f5b6b1a5b2d789e7c288d.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": "0906174d9768c635117f9f1260c247c1e08533df775f08a816a260cb3b8bf284", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce330481abb1b5373dabbb8cd29f91d13694b08bee703145f01a0d7917fed40d", "generation_seconds_batch": 23.4551556709921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2490143775939941, "target_z": 1.109374989629785, "ce": 6.086154937744141, "genuineness": 4.15588903427124, "identity": 0.598371148109436, "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_Elation/0906174d9768c635117f9f1260c247c1e08533df775f08a816a260cb3b8bf284.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "094cccc151b919e914a614ea7590ead0581b92a93dd5e9891f6ac30381a5d854", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "463a68cc4b3900a8552a0ef12b32f700394141691c029c2a07e53a943ebddf90", "generation_seconds_batch": 23.70061270997394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.372499704360962, "target_z": 1.2812501037021502, "ce": 5.3792572021484375, "genuineness": 3.4341442584991455, "identity": 0.2835419178009033, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/094cccc151b919e914a614ea7590ead0581b92a93dd5e9891f6ac30381a5d854.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "098735ce5dcc9e76b3f4278634053678d574446a7871bc01ba57fb5c3a141f73", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e62fa726f97fb8708576eb70a511c4d5e6801a9c81c1e4e72e1df000bcb0c7ee", "generation_seconds_batch": 19.244884423096664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3390123248100281, "target_z": -0.15722656314813843, "ce": 6.197352409362793, "genuineness": 4.375550270080566, "identity": 0.35098832845687866, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/098735ce5dcc9e76b3f4278634053678d574446a7871bc01ba57fb5c3a141f73.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "0a973150d8f26cf8a0e12a8903243a0d27f5217bc47f1d2f08a1de2a0c709ed3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cb10c35e2d9c3b91292559a43c91aacaf2fdeec0e2939aa87c1c7c3ee9d38962", "generation_seconds_batch": 16.228698365972377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5063185691833496, "target_z": 2.8593748237063448, "ce": 6.022613525390625, "genuineness": 3.785602569580078, "identity": 0.5819274187088013, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0a973150d8f26cf8a0e12a8903243a0d27f5217bc47f1d2f08a1de2a0c709ed3.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "0aa116f2039a541aaa944257c71dc18b28b1ed04e2e100502ce53173ab337fc2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5d094b326b3ab83eef4bd79a4ccf4e6cef4967bded8e948d8241f5318de30469", "generation_seconds_batch": 17.00338365091011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4174033403396606, "target_z": 1.34374997925957, "ce": 6.1894097328186035, "genuineness": 4.074300289154053, "identity": 0.5351287126541138, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0aa116f2039a541aaa944257c71dc18b28b1ed04e2e100502ce53173ab337fc2.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": "0b0b8818e6130c5bd098f9dfc2c22992a60144f48e7218e01a285dcbf421d0cf", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d23f36fc5f3b8f880320d19cc00330c952a83ea6cad9ecf36ae5f8037c2236c0", "generation_seconds_batch": 23.359847342944704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9450221061706543, "target_z": 2.078124968889355, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.6594575643539429, "hypothesis": "Les clés sont sur la table de la cuisine. Je regardais dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0b0b8818e6130c5bd098f9dfc2c22992a60144f48e7218e01a285dcbf421d0cf.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "0b44510537efde49cdea4b567642c83df584df6eeb4fc3db670cd870c1176ed2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "637f223e4d55d57b0f7f525955aeb2c2ba6a257c08ec25221d6f9dc92a97556d", "generation_seconds_batch": 25.967657349887304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.411790370941162, "target_z": 1.3359374740744625, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.4613300561904907, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0b44510537efde49cdea4b567642c83df584df6eeb4fc3db670cd870c1176ed2.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "0b6f3b9e3ce321682d8ddd7f69cf075c2442d3e98852a33d8dcd3776bc3503af", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71ffcc95da0081334b60454f1511e7435455cabb5b1dc883a55c702c68ee1533", "generation_seconds_batch": 23.967438363004476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.372499704360962, "target_z": 1.2812501037021502, "ce": 6.356205940246582, "genuineness": 4.193545341491699, "identity": 0.5480543971061707, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0b6f3b9e3ce321682d8ddd7f69cf075c2442d3e98852a33d8dcd3776bc3503af.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "0c16e87ec0cc7c2d04bf474a93d9cad17a6b6e73851e3df0370dafdaac206000", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fa420913ced8b7fc8b0f533a0fb0310cd3b9ef2fe3e37f789e1e01bde06a2b1c", "generation_seconds_batch": 22.944198927958496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15308284759521484, "target_z": -0.41601561074095433, "ce": 6.23706579208374, "genuineness": 4.344170093536377, "identity": 0.6084855794906616, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0c16e87ec0cc7c2d04bf474a93d9cad17a6b6e73851e3df0370dafdaac206000.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": "0c4da2f26f28dff094fc743e7af7f618d83f4db6ac7b9b375b50cea649f844c7", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The keys are on the kitchen table.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d531aa231437e14bd67ba20864f291b9a0745eeeceef455155415c09961fe114", "generation_seconds_batch": 17.926913241972215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8664405345916748, "target_z": 1.9687498962978498, "ce": 6.24500846862793, "genuineness": 3.600459337234497, "identity": 0.4708651006221771, "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_Elation/0c4da2f26f28dff094fc743e7af7f618d83f4db6ac7b9b375b50cea649f844c7.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "0c827c86d1fcffeab0bd343370cb68b185103851551ee2b3af8169e01514044d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9490fcafc1f0ddd0238241e56e5962f6afd967141aea2e66db8ffdbbdd6b9d0c", "generation_seconds_batch": 17.650390207068995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1671152412891388, "target_z": -0.39648438925904567, "ce": 6.221180438995361, "genuineness": 4.444586753845215, "identity": 0.511138916015625, "hypothesis": "La porte 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_Elation/0c827c86d1fcffeab0bd343370cb68b185103851551ee2b3af8169e01514044d.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "0caca56fec4aeb5ef0e461a3fe4129ae48a09242c8a396b14b8e002f183767d7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3508bfd057966c77d670c3d8e4ac5d0c66ea1a20601821ae9a5f9e00dbf5cfd3", "generation_seconds_batch": 23.416820472921245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4621467590332031, "target_z": 0.014160155277792342, "ce": 6.197352409362793, "genuineness": 4.519899368286133, "identity": 0.6476556062698364, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0caca56fec4aeb5ef0e461a3fe4129ae48a09242c8a396b14b8e002f183767d7.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "14e5c60a1632b5e475d4962c8dcef24462f0d7adc97de622579b343af41d24e2", "generation_seconds_batch": 18.263021891005337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10396939516067505, "target_z": -0.484374989629785, "ce": 6.062326908111572, "genuineness": 4.306513786315918, "identity": 0.49605777859687805, "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_Elation/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "0e065c6348cb0b438d4bdfaeafd21f59e84abfe5cb485e27270205cae6887a07", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5e4707ba6ab48034324334e8743db1df8bc08363fb80c49f7b36ea2804677fae", "generation_seconds_batch": 22.665447785984725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3668866157531738, "target_z": 1.2734374325936024, "ce": 6.221180438995361, "genuineness": 4.375550270080566, "identity": 0.6466251015663147, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0e065c6348cb0b438d4bdfaeafd21f59e84abfe5cb485e27270205cae6887a07.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "0e0c6574f58e22ce1367c1b0a3a14e1ee0afdaa63c650d957419cb7daf9a7bb8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cef61ce20cb4d74d135268591ec5089408caadef6c2c417fccf9b0ce1dd3168", "generation_seconds_batch": 23.369476519990712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0132699012756348, "target_z": 0.7812501037021502, "ce": 6.41180419921875, "genuineness": 4.168440818786621, "identity": 0.49322962760925293, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0e0c6574f58e22ce1367c1b0a3a14e1ee0afdaa63c650d957419cb7daf9a7bb8.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "0e590a40d5198b3940878a1762d2cf27fdbaaf013a10fdc6e948b97f28ea52ce", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "1594de252b4836904d911a001b9dd896b9d770a77f08aa1fa4e98db84c101047", "generation_seconds_batch": 25.264440363971516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5408885478973389, "target_z": 1.515624927408495, "ce": 5.3792572021484375, "genuineness": 3.3745219707489014, "identity": 0.3275294303894043, "hypothesis": "The door is still open! I put your coat on the chair! Tell me when you are ready!", "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_Elation/0e590a40d5198b3940878a1762d2cf27fdbaaf013a10fdc6e948b97f28ea52ce.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "0e807fbbe3f34b19bdceb2958aa29b56da5b109b2ec0174e1d02b2927317781b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bad3f306ad7c70beeaa1519a983ff0ea7d1f25e83e68278cb16b4b41e7162c98", "generation_seconds_batch": 21.646729439031333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1629055142402649, "target_z": -0.40234376814787626, "ce": 6.117925643920898, "genuineness": 4.15588903427124, "identity": 0.47810637950897217, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0e807fbbe3f34b19bdceb2958aa29b56da5b109b2ec0174e1d02b2927317781b.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "0f2f3452a059d5c032fc15d7a7719b749603f9a346e7447ff349f23dacc7a01f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "722583cb73d2c41b0df32395b12db5a9a49e03b50ea8af36b17d7e9644804cbe", "generation_seconds_batch": 24.84633823495824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2541162371635437, "target_z": -0.2753906003707393, "ce": 6.0305562019348145, "genuineness": 4.287685871124268, "identity": 0.31998223066329956, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0f2f3452a059d5c032fc15d7a7719b749603f9a346e7447ff349f23dacc7a01f.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "0f364d033621d0c6800761831fa254b545095d163c869d4b9ac5aa968c1d7aff", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f271187d167ec7a4856ae0f0c9b7ced67b3d30f000be5dd5b6b7dc42672d964a", "generation_seconds_batch": 23.314960247953422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23868057131767273, "target_z": -0.296874989629785, "ce": 6.141753673553467, "genuineness": 3.8671910762786865, "identity": 0.3264189064502716, "hypothesis": "The 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_Elation/0f364d033621d0c6800761831fa254b545095d163c869d4b9ac5aa968c1d7aff.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "0f4ca905becd1cbae0413b64981438b938a8dca9f599f81374f9f1e514ee601c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6b3883704b6317476d52a21f5eccffb9d2868c7ff50348ef454fc3b606363713", "generation_seconds_batch": 21.9697520469781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3332087993621826, "target_z": 1.2265624014829573, "ce": 6.300607204437256, "genuineness": 4.507347106933594, "identity": 0.5662356615066528, "hypothesis": "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_Elation/0f4ca905becd1cbae0413b64981438b938a8dca9f599f81374f9f1e514ee601c.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "0f9033f6a9236b8db8f5d42dd826f70689d5a13f1a12f929535ff6c3d77b3202", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f73c6f757e34b2a6885a3d81c12bf428c14b05ad1efa207665347c11caa862c9", "generation_seconds_batch": 23.427314288099296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6073520183563232, "target_z": 2.99999991703828, "ce": 5.808161735534668, "genuineness": 3.823258876800537, "identity": 0.5060423612594604, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0f9033f6a9236b8db8f5d42dd826f70689d5a13f1a12f929535ff6c3d77b3202.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "0f95e7ed5f4010053d60fdf05cf21543371f014dfa755b8bb2b4e872696e58e7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a066e59ed0b42b5b5b131f272d7df8b95422ecc56ef5d38f1c3b54e6144050f6", "generation_seconds_batch": 22.74488310702145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5579180121421814, "target_z": 0.1474609731476141, "ce": 6.086154937744141, "genuineness": 3.3494176864624023, "identity": 0.47900599241256714, "hypothesis": "The 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_Elation/0f95e7ed5f4010053d60fdf05cf21543371f014dfa755b8bb2b4e872696e58e7.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "0ff4a89cd24ee278a6c9fa2d38eed6d95d7a578e946f500d0dc7b20a7fbc23da", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d2d542746afdc385cd5f01c03c8fa27b88de2c07ac3773a0b387397a63f46198", "generation_seconds_batch": 27.358089277986437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.056389331817627, "target_z": 3.625, "ce": 5.323658466339111, "genuineness": 3.823258876800537, "identity": -0.003957189619541168, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/0ff4a89cd24ee278a6c9fa2d38eed6d95d7a578e946f500d0dc7b20a7fbc23da.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": "10264d06197ec2cae6eac9fd76e6575f4c5d14a899353189fd1c468ae816494a", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6f24bc8ff83f0ba853ac82ea3b05851d710ab7d019fecbc7bbc240ddc576d16", "generation_seconds_batch": 16.73858942592051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7985738515853882, "target_z": 0.48242182185264804, "ce": 6.173524379730225, "genuineness": 4.432034492492676, "identity": 0.6860940456390381, "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_Elation/10264d06197ec2cae6eac9fd76e6575f4c5d14a899353189fd1c468ae816494a.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "10947bfd7c70b7c8cf4d6f89a54dc153818a67d2403259463f5f5e7a17ab7da0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a7454adec1419fa2d66e0c6bf4b835da3dc3e02b2a2fdb7cb5a5ebd5eff87fbe", "generation_seconds_batch": 21.841958752949722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.888000249862671, "target_z": 3.3906248444467746, "ce": 5.728734970092773, "genuineness": 3.9676074981689453, "identity": 0.5599014759063721, "hypothesis": "I found the little box! It was beside the old window. We can look inside too!", "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_Elation/10947bfd7c70b7c8cf4d6f89a54dc153818a67d2403259463f5f5e7a17ab7da0.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "10c4e56332ae10c8764d64cde48aeb0a625b88644a084827a08ca185f560fb4c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45c9dc77b4593ee9bc9cd10d1938d8f38a1538bbbbf53b0f634547d75f9230de", "generation_seconds_batch": 18.562913847970776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1125190258026123, "target_z": 3.703125051851075, "ce": 5.166790962219238, "genuineness": 3.7542223930358887, "identity": 0.477226585149765, "hypothesis": "La puerta sigue abierta! He dejado tu abrigo sobre la silla. Dime cuándo estás listo!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/10c4e56332ae10c8764d64cde48aeb0a625b88644a084827a08ca185f560fb4c.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": "10dffd3317ee08d3ad90b18dfd26a14de8dcaea275397538c028b5a7ace5f258", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3546529aeabf168a8c7d81dab2d1768ddc6534aa7c8f7031212aa6a3c914a68", "generation_seconds_batch": 21.40774776902981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.299531102180481, "target_z": 1.1796875362957526, "ce": 6.070269584655762, "genuineness": 4.281409740447998, "identity": 0.6350963115692139, "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_Elation/10dffd3317ee08d3ad90b18dfd26a14de8dcaea275397538c028b5a7ace5f258.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "10e5f924a4ea2ecd41051d02192a1e8203c2a53c81b121179372c813f1463af5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a5979c563acc264ad7c973628177cc52810e61ae0253130e2fe68874ad0a5df4", "generation_seconds_batch": 21.029314663959667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2709551155567169, "target_z": -0.25195312629627686, "ce": 6.292664527893066, "genuineness": 4.356721878051758, "identity": 0.667116641998291, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/10e5f924a4ea2ecd41051d02192a1e8203c2a53c81b121179372c813f1463af5.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "11907c2f80e673d862af0c1095e8da1c41142e01ae0de078fc9eabfc9f05ebe6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9cf67ca564b8b71f6f8338e24f55a94387d0448ead16fbb5e341bf55162165f1", "generation_seconds_batch": 21.71195268095471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2705740928649902, "target_z": 2.53124993777871, "ce": 6.221180438995361, "genuineness": 4.005263805389404, "identity": 0.48028287291526794, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/11907c2f80e673d862af0c1095e8da1c41142e01ae0de078fc9eabfc9f05ebe6.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "11cd25097f23a2a2ef6e537875d74bf47b94a189fb63e7d65014cf8a6809395d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "52fe205566beaf52188abddac7350ccfa06f3c69acb9177da794db3900d7c41f", "generation_seconds_batch": 17.576559860957786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1474698781967163, "target_z": -0.42382811592606184, "ce": 6.252951145172119, "genuineness": 4.137060642242432, "identity": 0.4975607097148895, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/11cd25097f23a2a2ef6e537875d74bf47b94a189fb63e7d65014cf8a6809395d.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "11ec7975c9333c5b9d15b59479963bc838ad2d928d45585cf1f3e02b3e791f3c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "77d894627c26719e967de014a8da49bbfcb3b98244fd2223a9312a13802cbb5f", "generation_seconds_batch": 22.453645478002727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2818000316619873, "target_z": 2.546874948148925, "ce": 6.125868320465088, "genuineness": 4.030367851257324, "identity": 0.37289702892303467, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro de la casa.", "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_Elation/11ec7975c9333c5b9d15b59479963bc838ad2d928d45585cf1f3e02b3e791f3c.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "129ed6dcd524ae5954a6b5b14eb28f093fec4fc6582efe90f182ec727be33250", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bb2bf11b9c7f44ef5cb35e18f6b0685aa52451004bc374024c186329eb9482da", "generation_seconds_batch": 22.675372845027596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.248122215270996, "target_z": 2.49999991703828, "ce": 6.022613525390625, "genuineness": 3.8169827461242676, "identity": 0.7713203430175781, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/129ed6dcd524ae5954a6b5b14eb28f093fec4fc6582efe90f182ec727be33250.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "eab897bc5abd02e50e072f2721ec3ddb33d9338102b162954bddcd248594a4c0", "generation_seconds_batch": 19.258722561993636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2948102355003357, "target_z": -0.21874997925956996, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.7085558176040649, "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_Elation/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "13832685ffa0204fbab1497d6543dad5e22e335f87d7f82375020adaa3ab80db", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6a1e9914bb20b9e5890e848a060cc99b9ce1bd6ca85bb50cbbae174bf808af81", "generation_seconds_batch": 25.014552796958014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1919925212860107, "target_z": 2.421874865187205, "ce": 6.046441555023193, "genuineness": 4.287685871124268, "identity": 0.4244447946548462, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/13832685ffa0204fbab1497d6543dad5e22e335f87d7f82375020adaa3ab80db.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "139818304cc5fa3fea4b71756800b2065825a754e35e173c0a42342458c15cfd", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f651dd028d4ae6b97676832a819c52c3f9a43e9eca1aa2be6cd18b99936906d1", "generation_seconds_batch": 23.52139765699394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4342422485351562, "target_z": 1.3671874948148925, "ce": 6.173524379730225, "genuineness": 4.15588903427124, "identity": 0.36592897772789, "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_Elation/139818304cc5fa3fea4b71756800b2065825a754e35e173c0a42342458c15cfd.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "13c3aa5bc1317d57edfd22cd13af7a8a7250ba68676489b67a9e86cc1af30757", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aea84dd4a4bdcf9e0472e54801bd83a898ea659508f55259ebb5b972e9b5c227", "generation_seconds_batch": 22.960208195028827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7185891270637512, "target_z": 0.3710937474074463, "ce": 6.0146708488464355, "genuineness": 4.005263805389404, "identity": 0.6313700079917908, "hypothesis": "Ik 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_Elation/13c3aa5bc1317d57edfd22cd13af7a8a7250ba68676489b67a9e86cc1af30757.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "13e2da76482dcfd8897e0b12d545b66cc9003a76dc91efb0d01e3cfb2852f215", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "108648161060dc72c78f32a2edc33589bcad533f6c406318dfe186f6efa9fa64", "generation_seconds_batch": 17.3771092799725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1125190258026123, "target_z": 3.703125051851075, "ce": 5.7406487464904785, "genuineness": 3.8420867919921875, "identity": 0.535526692867279, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/13e2da76482dcfd8897e0b12d545b66cc9003a76dc91efb0d01e3cfb2852f215.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "14aef29917d08f18945513419423a5b1fe37f8fe83252517ada7b630e9abfa8a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d8da51b0e7d1af4910a82b2f6eddbd02620c77c6d20615fc6e3027de105beaad", "generation_seconds_batch": 22.44510543998331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3804079294204712, "target_z": -0.09960939962926066, "ce": 6.1020402908325195, "genuineness": 4.193545341491699, "identity": 0.615246057510376, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/14aef29917d08f18945513419423a5b1fe37f8fe83252517ada7b630e9abfa8a.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "14bbf401e4f85419b773b4df993deaaf05ee11648705ecb52f302f4d4b95f9be", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6d17066322df078f01bb99afa5b91c06f9e628e93b7490c045d4627cb09349fb", "generation_seconds_batch": 23.620763604994863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4061774015426636, "target_z": 1.328124968889355, "ce": 6.308549880981445, "genuineness": 4.3881025314331055, "identity": 0.3252107501029968, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/14bbf401e4f85419b773b4df993deaaf05ee11648705ecb52f302f4d4b95f9be.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "14ded877d59bcefa3c11a781c48fb94a0898368d8cf2c508c0a8abdff8c5a5f0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28fbb750e29550ce3409aa6af214a7770d9cef602c6f20d5635798f2dab05d3f", "generation_seconds_batch": 16.997988477931358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1134111881256104, "target_z": 2.3125001244425802, "ce": 5.982900142669678, "genuineness": 3.9299514293670654, "identity": 0.35725462436676025, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/14ded877d59bcefa3c11a781c48fb94a0898368d8cf2c508c0a8abdff8c5a5f0.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "ce82794489b56371605508fa9b02737f8dd2818f9002a82a767a1c52b21f139f", "generation_seconds_batch": 18.41770422994159, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06748512387275696, "target_z": -0.5351562318521237, "ce": 6.348263263702393, "genuineness": 4.218649387359619, "identity": 0.5831885933876038, "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_Elation/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "1615520c097d7f26368adc553f294acfdfbc5802ab078a45d99633e7e9be0a4b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "845839465c1f5acd86e98710af2a93d8577cb342fdcc64cdd72ffc0adba1f703", "generation_seconds_batch": 22.373601571074687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.214444398880005, "target_z": 2.4531248859276347, "ce": 6.348263263702393, "genuineness": 4.193545341491699, "identity": 0.42813563346862793, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1615520c097d7f26368adc553f294acfdfbc5802ab078a45d99633e7e9be0a4b.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "16ecfdd03e0d83ea72d702759e919c9553ec0b9d26c3b65b8b4bffb56221e5d0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f886060473f62bb84364d54d44a7c7bbf59c793ae58421e90a0de258fbbd5ba1", "generation_seconds_batch": 22.39607007394079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7036645412445068, "target_z": 1.7421874118531724, "ce": 6.054384231567383, "genuineness": 3.8546390533447266, "identity": 0.4556819200515747, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/16ecfdd03e0d83ea72d702759e919c9553ec0b9d26c3b65b8b4bffb56221e5d0.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "170a972867ec2f9435dc3f9e386ea487de0152f8588f9918771bd7036503401f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4447f2d4c3a48707a19beeeebdb6501bb7dcec1be03e4b95e666f97c7d5ef853", "generation_seconds_batch": 22.342944407020696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.090959310531616, "target_z": 2.28125010370215, "ce": 5.879645347595215, "genuineness": 3.9801597595214844, "identity": 0.12438879162073135, "hypothesis": "De deur staat nog open. Ik heb je juist op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/170a972867ec2f9435dc3f9e386ea487de0152f8588f9918771bd7036503401f.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": "1807b1b2793a3b322577644a5e7b217cdc2166b9dabec736c60f438ae9477e44", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The road turns left behind the bridge.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29181ef392bfae74c4897bdb432e5f9516d3b6925625c793086a73a6fa06e1f2", "generation_seconds_batch": 21.48520233493764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0730980634689331, "target_z": -0.5273437681478763, "ce": 6.483288764953613, "genuineness": 4.231201171875, "identity": 0.33673226833343506, "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_Elation/1807b1b2793a3b322577644a5e7b217cdc2166b9dabec736c60f438ae9477e44.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": "1920594c1c90c55fd6fe796aef7a74cf076ea640d1f611959726592c82eb6a6d", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90fd658e6d1b29e535486bc929a447f97aa45b01354d2b00cf7acc780d2df755", "generation_seconds_batch": 16.590294479974546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42741653323173523, "target_z": -0.034179689444415316, "ce": 5.998785495758057, "genuineness": 4.042920112609863, "identity": 0.6221705675125122, "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_Elation/1920594c1c90c55fd6fe796aef7a74cf076ea640d1f611959726592c82eb6a6d.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "19a9379a4192a2332f4659d341d0e2f9034d45e297e07cebcd009421c088fbf3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ce1d11472dfd7a440db6a3bd562b1176f5ac30254cb9dc144041d3aa8d10c985", "generation_seconds_batch": 22.545745374984108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7541813850402832, "target_z": 1.8125001244425802, "ce": 6.022613525390625, "genuineness": 4.174716949462891, "identity": 0.5000907778739929, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/19a9379a4192a2332f4659d341d0e2f9034d45e297e07cebcd009421c088fbf3.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "19dadd928d8398fbf0d6c0ba4081688bbf6ba2f697996688f91f76b3e9963a56", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c9dab16dc93bbdbceb09a3aa1d60dd4eb9bfcd32f223a6caf76884ad39a3d066", "generation_seconds_batch": 16.56249330402352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3267037868499756, "target_z": 2.609374989629785, "ce": 6.308549880981445, "genuineness": 4.105680465698242, "identity": 0.5637503266334534, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/19dadd928d8398fbf0d6c0ba4081688bbf6ba2f697996688f91f76b3e9963a56.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": "1a27ea718a5bad4ea4ba69556e844ce3fc72ae1f1ab634e9d83d0605b5047412", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e92e91fd16c3a58e24ba46d30dde600558db8b8f8277bb0d53d1f0304bbe512", "generation_seconds_batch": 19.130675061023794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4007549583911896, "target_z": -0.07128904759281592, "ce": 6.372091293334961, "genuineness": 4.381826400756836, "identity": 0.7774221897125244, "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_Elation/1a27ea718a5bad4ea4ba69556e844ce3fc72ae1f1ab634e9d83d0605b5047412.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "1af684ccc74ede1de1237d024fcc66694258652bbd611b2c0cbcda369c7322e6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24a215afff6956274c38f73d6b735a0627adc04f837530168073e31ebc2767ed", "generation_seconds_batch": 21.51670604699757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.078841209411621, "target_z": 3.65625002074043, "ce": 5.744620323181152, "genuineness": 4.005263805389404, "identity": 0.505113959312439, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1af684ccc74ede1de1237d024fcc66694258652bbd611b2c0cbcda369c7322e6.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "1b03ba2fb243fa933519e3a554c0dc03b319282e35a4600bc564841561588049", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 131, "seconds_generated": 10.48, "mp3_sha256": "53e185ad61a212cf6979f75f4c8231b266f2326c70fa238a298cdee2ec5bc8a6", "generation_seconds_batch": 22.727706743986346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.921678066253662, "target_z": 3.4374998755574198, "ce": 5.363371849060059, "genuineness": 3.5596652030944824, "identity": 0.2736409902572632, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.", "wer": 0.06666666666666667, "duration_error_s": 0.28000000000000114, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1b03ba2fb243fa933519e3a554c0dc03b319282e35a4600bc564841561588049.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "1b383fe6076adcb818e33fee6963a8daca72949515663153a8bbeae7471db263", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3ce83c2268ac46bf93c7d073211152ec9c1fa0d8acd0d6af3d5dcebb6c9379f7", "generation_seconds_batch": 15.955135722993873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5852811932563782, "target_z": 0.18554687370372314, "ce": 6.070269584655762, "genuineness": 4.268857479095459, "identity": 0.5901097655296326, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1b383fe6076adcb818e33fee6963a8daca72949515663153a8bbeae7471db263.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "1b512b09d6a7165f2273dc5dd4ecb5d7105aaf5435386b96138b49784a4c8682", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f2f2f896203807ee81f3d50e117bd34c0599ccd4b5c34ac4d424d02736010784", "generation_seconds_batch": 22.193225017981604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1704328060150146, "target_z": 0.9999999170382798, "ce": 5.967014789581299, "genuineness": 3.71028995513916, "identity": 0.5878391265869141, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1b512b09d6a7165f2273dc5dd4ecb5d7105aaf5435386b96138b49784a4c8682.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "1b95291e843b2205481dcd93a7610a320e9de91762d78ac5738e2a93f53d1557", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "80f59009cd37359eac015063b54988334132f2c60ff1a32a47b2a4f81b28c004", "generation_seconds_batch": 20.4036695510149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9450221061706543, "target_z": 2.078124968889355, "ce": 5.8875885009765625, "genuineness": 3.760498285293579, "identity": 0.4218428134918213, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1b95291e843b2205481dcd93a7610a320e9de91762d78ac5738e2a93f53d1557.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "1ba5dd65f286e6a02da5d711c81d66f55c65c4d8e35fc6fafbb4f6c1d380f283", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "33f608ce16121c6e72bd98c0b661c12dff814b828c1e35fc7f69312e3c41a14f", "generation_seconds_batch": 17.108104030019604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.67508864402771, "target_z": 0.31054687370372314, "ce": 6.078212261199951, "genuineness": 4.036643981933594, "identity": 0.522754967212677, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1ba5dd65f286e6a02da5d711c81d66f55c65c4d8e35fc6fafbb4f6c1d380f283.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "1c45bbb371f318258de6e772b1004d7357fb2a475cc4f16072566998203923ba", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "94271a3b70e206c4a29556e0cfc831f29c545ea968f6936bdd9614a60c4bc3a4", "generation_seconds_batch": 23.14547524799127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0946578979492188, "target_z": 0.8945313459244889, "ce": 6.109982967376709, "genuineness": 4.024092197418213, "identity": 0.3104800581932068, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1c45bbb371f318258de6e772b1004d7357fb2a475cc4f16072566998203923ba.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "1c4ec6bc26735c083cc83f83f0321ca796a07d5113a52f62d2ee0a9e7f646468", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f5d7e4a8a95c805d038ec114a245ac10b4ed403f17eedda71c911b682dfa165", "generation_seconds_batch": 23.014920226996765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2265625, "target_z": 1.078124968889355, "ce": 5.998785495758057, "genuineness": 3.8295347690582275, "identity": 0.4906577467918396, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1c4ec6bc26735c083cc83f83f0321ca796a07d5113a52f62d2ee0a9e7f646468.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "1c6a3a36493a40c2549e557a4cb0f72fb64afeb3874a01d3c6d3a89e52758878", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e426d34ac347f97bd7bcb7cbb398c0c04a76519ccce15201e8296ea1c28d150a", "generation_seconds_batch": 23.072556155035272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03942027688026428, "target_z": -0.5742187577776613, "ce": 6.09409761428833, "genuineness": 4.507347106933594, "identity": 0.34487083554267883, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1c6a3a36493a40c2549e557a4cb0f72fb64afeb3874a01d3c6d3a89e52758878.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "1c958505d3b8fe19056c83710338dc755f001783b69ac24a8110dd2aa1d1fc19", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9b8e43c63d0f878df97a752dcfa2e0228f8e5814714d48cf485de5d50f54ebe4", "generation_seconds_batch": 20.99730434594676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0581735372543335, "target_z": 0.84374997925957, "ce": 5.49045467376709, "genuineness": 3.5565271377563477, "identity": 0.27415406703948975, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1c958505d3b8fe19056c83710338dc755f001783b69ac24a8110dd2aa1d1fc19.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "1ca9718d2cc7ff86afd6ed7c4a19571868db086ae8d292eebaed130cabbdf991", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bb87168467af5d6b5a3b0e72da3e9d12ba3b3d9aea49e6f9d14d607668a30634", "generation_seconds_batch": 21.87656118592713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8318705558776855, "target_z": 3.3124997925956996, "ce": 5.911416053771973, "genuineness": 4.105680465698242, "identity": 0.5105807781219482, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1ca9718d2cc7ff86afd6ed7c4a19571868db086ae8d292eebaed130cabbdf991.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "1cbea49670451f53e837190c9742e24ce85a10f0614037de7494d24a689990c2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5a5d63d8529074c01d02f06d87b85b44ec77728ceaeef901f61bafdac2c07e57", "generation_seconds_batch": 23.273979414021596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13343745470046997, "target_z": -0.44335937888883065, "ce": 6.149696350097656, "genuineness": 4.444586753845215, "identity": 0.5402662754058838, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1cbea49670451f53e837190c9742e24ce85a10f0614037de7494d24a689990c2.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "1cfd9561a79312d320a1ad5f4e48c6b0a1e63673ca94e50f9d445a6919f93cdd", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "697567fafe4e2cf76fedbc2697b90ad0fcc014c3b15e319f3afc82b36e20e354", "generation_seconds_batch": 16.40843816800043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7354280352592468, "target_z": 0.39453126296276875, "ce": 6.459460258483887, "genuineness": 4.20609712600708, "identity": 0.498227059841156, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1cfd9561a79312d320a1ad5f4e48c6b0a1e63673ca94e50f9d445a6919f93cdd.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": "1d1418ba6770117ddcc990b9431befea67affa822f816c9da7590afc78fe9139", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The keys are on the kitchen table.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7ffa83ac43065ef040d41118141f7eb5a4736adc7bc4bf43c9634b84e79bc33", "generation_seconds_batch": 16.107184757012874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2653421461582184, "target_z": -0.2597656314813844, "ce": 6.403861999511719, "genuineness": 4.325342178344727, "identity": 0.26867908239364624, "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_Elation/1d1418ba6770117ddcc990b9431befea67affa822f816c9da7590afc78fe9139.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "1d352add92a1f67c529a30f41c40a994be069f2e4818d7184515d3b79a46140a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5d2905c7cd96c14f548ca4c0c444d0c2a68f5782bd87160f68de5482068c1f41", "generation_seconds_batch": 21.85982440900989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1816587448120117, "target_z": 1.015624927408495, "ce": 6.070269584655762, "genuineness": 4.482243061065674, "identity": 0.468874454498291, "hypothesis": "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_Elation/1d352add92a1f67c529a30f41c40a994be069f2e4818d7184515d3b79a46140a.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "1d42c7b48e548315f129c68f954d84aa04e505ebc346025dda0eb9dd2a6a9b5a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f202394e5056511704ea13c43a1f4b04bbacced692be711b9fd7e071307fd9d1", "generation_seconds_batch": 16.975781638058834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9010105133056641, "target_z": 0.625, "ce": 6.213237762451172, "genuineness": 4.256305694580078, "identity": 0.5226154327392578, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1d42c7b48e548315f129c68f954d84aa04e505ebc346025dda0eb9dd2a6a9b5a.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "1d44f3545396d67f9f32cee1e1a8ffbc9b66e18b6f361352e2afdefdffddf7ae", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "52f3951368c21ef5395b4544256cc6f32980244c1c3c9debb0d46559deb5b166", "generation_seconds_batch": 17.650390207068995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38391605019569397, "target_z": -0.09472656314813843, "ce": 6.229123115539551, "genuineness": 4.105680465698242, "identity": 0.7547388672828674, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1d44f3545396d67f9f32cee1e1a8ffbc9b66e18b6f361352e2afdefdffddf7ae.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "a936a53ee2dd2217030bf6eb5f02df5dd931eed40fd183f92424b7d6d837b638", "generation_seconds_batch": 16.996843660017475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33690744638442993, "target_z": -0.1601562733329838, "ce": 6.38797664642334, "genuineness": 4.469690799713135, "identity": 0.5021432638168335, "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_Elation/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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "8c79f467a46eef523c022957a5a93074464356e3be5e4cf309c7c2d82c3299c4", "generation_seconds_batch": 17.62010373699013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12501800060272217, "target_z": -0.4550781366664919, "ce": 6.348263263702393, "genuineness": 4.432034492492676, "identity": 0.63277667760849, "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_Elation/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "1e35c79342fa2662480beffee6c00b11b5b726ab6b1219c1e37f201fe3cb6388", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb6845dc8b2f0b11eab874e167dbdc556b848c0cac6536925b71d7c707afdd90", "generation_seconds_batch": 22.80975674802903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.237788438796997, "target_z": 1.09374997925957, "ce": 6.23706579208374, "genuineness": 3.9425034523010254, "identity": 0.41256463527679443, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1e35c79342fa2662480beffee6c00b11b5b726ab6b1219c1e37f201fe3cb6388.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "9afd7902aa4c82a556e6324a551bf5d6be4a9914b3c90cac0b1ef67152243f83", "generation_seconds_batch": 16.996843660017475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35795608162879944, "target_z": -0.13085937888883062, "ce": 6.157639026641846, "genuineness": 4.293961524963379, "identity": 0.4568995237350464, "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_Elation/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "1fb25097efb4a60094c57d26979c4fa771f9d3ff4480bb490be0110c5f249cd8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5e2af88a2e5bbaa27328b979ed25ff2da94120649cbbb419ec3965969121626e", "generation_seconds_batch": 22.342944407020696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8196225166320801, "target_z": 0.5117187577776613, "ce": 6.157639026641846, "genuineness": 4.168440818786621, "identity": 0.519066333770752, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/1fb25097efb4a60094c57d26979c4fa771f9d3ff4480bb490be0110c5f249cd8.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "2044246860a810f54b6b83f776729bb63ae0684b14b486b67faf65e76ba4bc9d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0c834020b6ff308ebf94127900d632933ffb93b9eaeab6798b6123173d195239", "generation_seconds_batch": 24.316846782923676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8327627182006836, "target_z": 1.9218748651872049, "ce": 6.0146708488464355, "genuineness": 3.773050308227539, "identity": 0.3609989881515503, "hypothesis": "The 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_Elation/2044246860a810f54b6b83f776729bb63ae0684b14b486b67faf65e76ba4bc9d.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "2050e24c1fdc7cac0eab06caa42c64007f61ca52b3f772a4713e62aa6d4a5e5a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "36c5fa5bde0840d5588e71a36f3280d00930990fb64026a81e7a85b5c0e11603", "generation_seconds_batch": 22.34854559705127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0011518001556396, "target_z": 2.15625002074043, "ce": 5.7406487464904785, "genuineness": 3.8797430992126465, "identity": 0.47204768657684326, "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_Elation/2050e24c1fdc7cac0eab06caa42c64007f61ca52b3f772a4713e62aa6d4a5e5a.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": "205151537e435980573ad5d01af970929a00f8a21eb2208efe8a82a0460c4e11", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f5ee400df5027ee030597b01e7a37b917c66da8683d41c060ced0149dc285315", "generation_seconds_batch": 21.13838299701456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5614261031150818, "target_z": 0.15234376814787629, "ce": 6.1894097328186035, "genuineness": 4.356721878051758, "identity": 0.667191743850708, "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_Elation/205151537e435980573ad5d01af970929a00f8a21eb2208efe8a82a0460c4e11.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": "20c1a644c42cb04cf9e17857ae17d093691e3f00d5284e6a4a0a8089bac021c3", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The road turns left behind the bridge.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02a053cfaaecc9fca83bb4853a8edcd311e7d81ba8eb3a4ef1fa312585d3ab8a", "generation_seconds_batch": 15.50870164996013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1797444224357605, "target_z": -0.3789062525925537, "ce": 6.4515180587768555, "genuineness": 3.8922953605651855, "identity": 0.3558099567890167, "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_Elation/20c1a644c42cb04cf9e17857ae17d093691e3f00d5284e6a4a0a8089bac021c3.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "20cc5585b8a9688ac9397f16eb3496fe57b56ec96ca58e31dd0427f2f6012bce", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "99caa10ae8178be97adada48d6bc5b37e978291156ea2fbccf4ee3b4cee95789", "generation_seconds_batch": 23.45025293598883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1695406436920166, "target_z": 2.3906248444467746, "ce": 6.213237762451172, "genuineness": 4.036643981933594, "identity": 0.4929386079311371, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/20cc5585b8a9688ac9397f16eb3496fe57b56ec96ca58e31dd0427f2f6012bce.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "20dada50956d0075c20e63d1837271f385f4b7c657320a49f532d37d08c02d56", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f17a2d0e91dfcbbaa1fa863fdfc4e1805899acf0cf1539a2d8795dcd4adc2d5a", "generation_seconds_batch": 22.464588536066003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.596126079559326, "target_z": 2.984374906668065, "ce": 6.284721851348877, "genuineness": 3.8420867919921875, "identity": 0.3784521818161011, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschaffen!", "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_Elation/20dada50956d0075c20e63d1837271f385f4b7c657320a49f532d37d08c02d56.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": "212716777ae71c1296e975517b98eb4bf6ba60ca780de8a3e49b6e2d32cafe9f", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2b9d23f60d377b9f39387853913a3a5fd7ddd0c4f55a366e7b96ef1f8f69747", "generation_seconds_batch": 16.822991678956896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24429352581501007, "target_z": -0.2890625051851075, "ce": 6.284721851348877, "genuineness": 4.406930446624756, "identity": 0.6465792655944824, "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_Elation/212716777ae71c1296e975517b98eb4bf6ba60ca780de8a3e49b6e2d32cafe9f.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "223b2131be44703833a74d8f5c0920f38e3bc768eb24da1926980dc5ca95f1fa", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "dc3bf29498c3b7100ad276b72f5488a5023b0c7ae85582b566c802b3c1ab952c", "generation_seconds_batch": 21.180912518990226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7466539144515991, "target_z": 0.41015619037126366, "ce": 6.109982967376709, "genuineness": 4.011539936065674, "identity": 0.4819561243057251, "hypothesis": "Ik 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_Elation/223b2131be44703833a74d8f5c0920f38e3bc768eb24da1926980dc5ca95f1fa.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "2247bffc7e3e3a1caee0fa69a190bb00cced3465e98abeafa3ed011928a1126c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "60367a93e5a61e2c978f3f1838c00604362b5ec0a213cbc33d49fd51f105e45a", "generation_seconds_batch": 22.531889655045234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1984977722167969, "target_z": 1.0390626088872577, "ce": 6.09409761428833, "genuineness": 4.024092197418213, "identity": 0.31035900115966797, "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_Elation/2247bffc7e3e3a1caee0fa69a190bb00cced3465e98abeafa3ed011928a1126c.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "228eddbc0699eb0b49f7951a389877ce5f4de44014fb2f7365caa41c5af21143", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1fad06feb5d88661dcee57b14305561ecc775c42ad0b979f09162bc52133571b", "generation_seconds_batch": 24.107150188996457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9515272378921509, "target_z": 0.6953125466659675, "ce": 6.213237762451172, "genuineness": 3.6914620399475098, "identity": 0.2667033076286316, "hypothesis": "The 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_Elation/228eddbc0699eb0b49f7951a389877ce5f4de44014fb2f7365caa41c5af21143.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "229546f3783922962707257c51adf88b6b21bbb0f90644ef2ab68269100c6d02", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "db22d1339fa7d050c5c3b7f038b3c815723ed40146a1c53a88e26f83d9d59808", "generation_seconds_batch": 21.85247058409732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7620896100997925, "target_z": 0.43164062111116935, "ce": 6.499174118041992, "genuineness": 3.9927117824554443, "identity": 0.5557311773300171, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/229546f3783922962707257c51adf88b6b21bbb0f90644ef2ab68269100c6d02.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "229ff0b29e107e52087dc08368ccc3dca2c596ade02203e0f3503ab25862d577", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "63b17ae79e93432ff483a0c89df747707f09ebdcf0b17387deb5329408d257a3", "generation_seconds_batch": 23.01738126692362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0244958400726318, "target_z": 0.7968751140723652, "ce": 5.998785495758057, "genuineness": 3.9173994064331055, "identity": 0.4075813889503479, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/229ff0b29e107e52087dc08368ccc3dca2c596ade02203e0f3503ab25862d577.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "238872c0a309763057e5d5f8fcfd0a7a56d98266a9ef0f8c37fff049b9f5cc12", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4c04dc62d7c5d86a7003ddcb033a43e2ce25014d4f644da5ca795771590336bf", "generation_seconds_batch": 22.982680657994933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.411790370941162, "target_z": 1.3359374740744625, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.6654366254806519, "hypothesis": "La porte 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_Elation/238872c0a309763057e5d5f8fcfd0a7a56d98266a9ef0f8c37fff049b9f5cc12.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": "23e14020c2d9952dbcf9baff375b7bf710f15b0bacc3fb1cc66d0a8fa27ed7cf", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Escribí el número en el sobre.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c631dc6a836e0b39d01c261f7e0efbae9858cd853724da830abc88cc176fac04", "generation_seconds_batch": 21.176260918029584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.563340425491333, "target_z": 1.546874948148925, "ce": 6.197352409362793, "genuineness": 4.193545341491699, "identity": 0.6777437329292297, "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_Elation/23e14020c2d9952dbcf9baff375b7bf710f15b0bacc3fb1cc66d0a8fa27ed7cf.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "2457e7e6e3f42cfa357dfbece01bdc9e0724bb04a2fa9e6e2f0ad89003b7dfba", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "60da8e348d4469b6f041377d3fe3efbef3c863e3a2c5c289bbca3e1dfb07114f", "generation_seconds_batch": 23.573504457017407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4877559244632721, "target_z": 0.04980469981463033, "ce": 6.173524379730225, "genuineness": 4.356721878051758, "identity": 0.6680362820625305, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2457e7e6e3f42cfa357dfbece01bdc9e0724bb04a2fa9e6e2f0ad89003b7dfba.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "25d04dff45c004f664e6cb874e12f1346da41a3b9e80d6a928da786a51844dc1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9c04f903456ef166147ad7ec59f378b45e1b13cc445c1d160535cf2dc520e649", "generation_seconds_batch": 17.01318338396959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9515272378921509, "target_z": 0.6953125466659675, "ce": 5.542081832885742, "genuineness": 4.068024158477783, "identity": 0.6037383675575256, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/25d04dff45c004f664e6cb874e12f1346da41a3b9e80d6a928da786a51844dc1.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "260509fb2f7e175ea5d7b9452568a3dea27a6a60e3e17098fa4de28cd6fe6f1f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c3b07c0126fc9d2e58d2cf6bb38fa0d84ca0313bc2f58ccfc41d98ebdbee264d", "generation_seconds_batch": 22.422820423031226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3500478267669678, "target_z": 1.2500000829617202, "ce": 5.919358730316162, "genuineness": 3.973883628845215, "identity": 0.5407697558403015, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/260509fb2f7e175ea5d7b9452568a3dea27a6a60e3e17098fa4de28cd6fe6f1f.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "261c311c20f755afb76ef203338f8cd075db5520524ac3ee5b90b1fcb3f5e9a7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4f6dcfd2cc595f3c2db48f459d59d1eb9191515b064b8c83227018f37dfe719a", "generation_seconds_batch": 25.473580107907765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5154699087142944, "target_z": 0.08837887157459354, "ce": 6.2767791748046875, "genuineness": 4.369274139404297, "identity": 0.734049379825592, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/261c311c20f755afb76ef203338f8cd075db5520524ac3ee5b90b1fcb3f5e9a7.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "eab8125fea017aca3b26d5b673b586da6e80a116ed61282f634a74240b1174e3", "generation_seconds_batch": 17.017267839983106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06748512387275696, "target_z": -0.5351562318521237, "ce": 6.395919322967529, "genuineness": 3.9676074981689453, "identity": 0.2651383578777313, "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_Elation/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "26de1be56fbc9f9fcb2233af7075d5a2cc3d69fffa464dfc598f0b533501a08e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "af884a3837eb46cf349e92cd468832bef303eed94d2e3fc19ad2be624c150557", "generation_seconds_batch": 22.514615427004173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2490143775939941, "target_z": 1.109374989629785, "ce": 6.070269584655762, "genuineness": 4.369274139404297, "identity": 0.5839741826057434, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/26de1be56fbc9f9fcb2233af7075d5a2cc3d69fffa464dfc598f0b533501a08e.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "27956436df9614aef8992179d03495a90845ed629c0df9affe336caf82b107b8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f9871ecd0a6da9840ea5bb29b9f6498b5eae8c917b5d1050e0ae6e1ad9edbe30", "generation_seconds_batch": 17.64776532794349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4566941261291504, "target_z": 1.3984375155553226, "ce": 6.395919322967529, "genuineness": 4.306513786315918, "identity": 0.47131678462028503, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/27956436df9614aef8992179d03495a90845ed629c0df9affe336caf82b107b8.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "280e9ffe499bfe0efc5fcb8b5f11d5387f088c3408ccea831608f2f7a3088d83", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bb2b6f723b98083fa0194196fd1b1c7c8ead9b26b18479594dd22c99d8202b53", "generation_seconds_batch": 23.273979414021596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41548898816108704, "target_z": -0.050781242222338735, "ce": 6.348263263702393, "genuineness": 4.18099308013916, "identity": 0.5948066115379333, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/280e9ffe499bfe0efc5fcb8b5f11d5387f088c3408ccea831608f2f7a3088d83.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "286a47a3252bae6d2ab5e1f6a5734a97d7dd702a757674b3d2abe0042b8d0509", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "953f6f28465e0b3e4bec7b46c7e3585e0924aca571df2bcaf7b5b54e44ce0c2a", "generation_seconds_batch": 15.82979614904616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9899258613586426, "target_z": 2.140625010370215, "ce": 5.748591423034668, "genuineness": 3.986435890197754, "identity": 0.44679397344589233, "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_Elation/286a47a3252bae6d2ab5e1f6a5734a97d7dd702a757674b3d2abe0042b8d0509.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "287123ebec6bb13665985425a2059b5749519ec85bb8d7407e98eada39b32beb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fd3d28cbd02363bcc870062cce46d2d6c71751dc0f5612676cfef9c00da086a0", "generation_seconds_batch": 23.696735656936653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8543224334716797, "target_z": 3.34374981333613, "ce": 6.117925643920898, "genuineness": 4.030367851257324, "identity": 0.4998241066932678, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/287123ebec6bb13665985425a2059b5749519ec85bb8d7407e98eada39b32beb.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "288adf58fcfb6a13468045b1ba5e94b1aa1ea8cf12e25da912c44ca7afe2fa5d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "dcb210113b08006c8f947046a94122f567a5b1c94a8e2a771120619bc0ce1979", "generation_seconds_batch": 24.14670889498666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6643738746643066, "target_z": 1.68750004148086, "ce": 5.8875885009765625, "genuineness": 4.118232727050781, "identity": 0.3167361319065094, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás linda.", "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_Elation/288adf58fcfb6a13468045b1ba5e94b1aa1ea8cf12e25da912c44ca7afe2fa5d.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": "28dc87780cb15ea8dd72826f4daa962bc92747c0f081243663157ea4a0785799", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b14b5675d4660058bf9a78f683f09feca10ce26449b93981c8b779dc498d125c", "generation_seconds_batch": 21.854495859937742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1928846836090088, "target_z": 1.0312499377787099, "ce": 6.078212261199951, "genuineness": 4.086852550506592, "identity": 0.4843868911266327, "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_Elation/28dc87780cb15ea8dd72826f4daa962bc92747c0f081243663157ea4a0785799.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "28df244f222049e49a48ad1f8e74d9ee06bfad32a6cc1e5c7ec2c4ef03517399", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b3daefdb289caa027cd64942147f0cda58dc6672cd6346e3ece8f6ea2cc362e0", "generation_seconds_batch": 23.12384905689396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2906004786491394, "target_z": -0.22460939962926066, "ce": 6.09409761428833, "genuineness": 3.936227321624756, "identity": 0.4628806710243225, "hypothesis": "The 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_Elation/28df244f222049e49a48ad1f8e74d9ee06bfad32a6cc1e5c7ec2c4ef03517399.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "29067b4e80bdc0feb62ab7b2c21f100a860a196a79adb66695a16560c7feffca", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c2de66893f2f37fb47b5f660be110a24cb2b496d5ed516a85a6635fff4b6767d", "generation_seconds_batch": 24.192724611028098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.887108087539673, "target_z": 4.781249771855269, "ce": 5.164804935455322, "genuineness": 3.565941095352173, "identity": 0.32528606057167053, "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_Elation/29067b4e80bdc0feb62ab7b2c21f100a860a196a79adb66695a16560c7feffca.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "291a58df0eee9e8557ac10c10c52da40f30cfbde19848f0c781fa716371b4605", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d42d3bdc95cc8ccf84fdc81afb2f60865aa9d8dfb0ef0d92c4a715e270009bbe", "generation_seconds_batch": 17.012443554005586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8308484554290771, "target_z": 0.5273437681478763, "ce": 6.062326908111572, "genuineness": 4.093128204345703, "identity": 0.5461329221725464, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/291a58df0eee9e8557ac10c10c52da40f30cfbde19848f0c781fa716371b4605.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "2ac791f1397ffe7c0b65104c27d834e673d811c13f7e08b9973e574378cd56fa", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "457fa410fa2a7010289cd9158ee0a049227dfd8bc2d4e259e717c128c6d26414", "generation_seconds_batch": 22.65333817899227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.394951581954956, "target_z": 1.3125001244425802, "ce": 6.109982967376709, "genuineness": 3.7165660858154297, "identity": 0.5874796509742737, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2ac791f1397ffe7c0b65104c27d834e673d811c13f7e08b9973e574378cd56fa.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "2ae2a35c5717ca2dbc8d5021337913c1953749296e2fd5fbccc380f41c4848af", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a72e6d69c45a858e50a76f9f5e1b90af7d934b630626c637c2971f534d95d848", "generation_seconds_batch": 17.045304328086786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7733155488967896, "target_z": 0.4472656314813844, "ce": 5.7684478759765625, "genuineness": 3.5973212718963623, "identity": 0.6396402716636658, "hypothesis": "The 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_Elation/2ae2a35c5717ca2dbc8d5021337913c1953749296e2fd5fbccc380f41c4848af.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "2ae5d83641bf110d0ae483ac682fe4ff83ce70243841f58ddfa117efebcba7af", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cd4a94e346ccb414b35f1c793a61fdfdbfc0877d061e74438416298d4004459d", "generation_seconds_batch": 17.496147500933148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7990849018096924, "target_z": 1.8749998340765597, "ce": 5.959072113037109, "genuineness": 3.8922953605651855, "identity": 0.4649868607521057, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2ae5d83641bf110d0ae483ac682fe4ff83ce70243841f58ddfa117efebcba7af.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "2b142f242d23ba9be7ff2c54cc61ed7a61fb607888c5c411823c38d5ca67bee1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8a1913c0d45b5625ca5675770eef7a1fe158a8d97d4500e635e736c013a71155", "generation_seconds_batch": 23.023645670968108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26393890380859375, "target_z": -0.26171875777766124, "ce": 6.268836498260498, "genuineness": 4.507347106933594, "identity": 0.6403710842132568, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2b142f242d23ba9be7ff2c54cc61ed7a61fb607888c5c411823c38d5ca67bee1.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "2b569d6e2a841fafcbee474b45094da6180794c5362c9b01ce68d19be0291ea2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c32c19f5b2bf9e258ad0d8ac8f23f07652587ece7b9f7773523b8902206807ef", "generation_seconds_batch": 22.974442468956113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9337961673736572, "target_z": 2.06249995851914, "ce": 6.125868320465088, "genuineness": 4.15588903427124, "identity": 0.515376091003418, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2b569d6e2a841fafcbee474b45094da6180794c5362c9b01ce68d19be0291ea2.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "2bbe8b25e667cf03885f009c7b97482b55a45c72579db09372da590721a09ad9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a8d461f904296165c371182f349606b823e06f2fbb0d8c7b44a02492334fafa", "generation_seconds_batch": 17.360641640028916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.557727575302124, "target_z": 1.5390626088872577, "ce": 6.419747352600098, "genuineness": 4.218649387359619, "identity": 0.4700378179550171, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2bbe8b25e667cf03885f009c7b97482b55a45c72579db09372da590721a09ad9.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "2c56d3c4f74aed0eb35d133a7e3ed7be3dfff4b238c680f4b845f08541c3a8b4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8707b971ba59c6f6b377c46268e7b9e0a327edb334ddfa115936c5abce093f4e", "generation_seconds_batch": 20.994528125040233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.876774311065674, "target_z": 3.3749998340765597, "ce": 5.927301406860352, "genuineness": 4.005263805389404, "identity": 0.5456271171569824, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2c56d3c4f74aed0eb35d133a7e3ed7be3dfff4b238c680f4b845f08541c3a8b4.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": "2c7eb71127f156da4ca4081e73501306542bd6c9330a73587675d2a69c1d8924", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "422e8f6b0b2398c2f74d663c7086071fee054cc510aad0a4a2eb61608a2053d5", "generation_seconds_batch": 23.15479520696681, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209723711013794, "target_z": 1.0546876192574728, "ce": 6.213237762451172, "genuineness": 3.672633647918701, "identity": 0.3583706021308899, "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_Elation/2c7eb71127f156da4ca4081e73501306542bd6c9330a73587675d2a69c1d8924.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "2cefafa7871e8ca1285035ec0845f26e9eb546e87ccd12f437cf406390b39472", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "65d0e02ca12086136ca6ebe898d20828586086a0f703e86446078ae36a43fb8b", "generation_seconds_batch": 17.11703216598835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2939181327819824, "target_z": 1.171875031110645, "ce": 5.982900142669678, "genuineness": 3.9425034523010254, "identity": 0.2576583921909332, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2cefafa7871e8ca1285035ec0845f26e9eb546e87ccd12f437cf406390b39472.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": "2d387e869a1258fb065ae4faddd5fd8b5960ae3bc764a3350cf41ddad19694d1", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90ec6cc62842386a1bd3074c69d10727ba2d93e520680e76e8321a6ee4a87a0a", "generation_seconds_batch": 21.318990878062323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7747187614440918, "target_z": 0.4492187162968012, "ce": 6.213237762451172, "genuineness": 4.344170093536377, "identity": 0.5807219743728638, "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_Elation/2d387e869a1258fb065ae4faddd5fd8b5960ae3bc764a3350cf41ddad19694d1.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "2dbf263687297f1db4cbb9a27e9a6aeea77c32e0f8c88121b31bf0f3c6f13143", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4e21b853b79b6931233d71588e6baac14aa632a18faf84f829bd499fee512668", "generation_seconds_batch": 21.51670604699757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6747076511383057, "target_z": 3.09374997925957, "ce": 5.808161735534668, "genuineness": 3.9048471450805664, "identity": 0.4215754270553589, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2dbf263687297f1db4cbb9a27e9a6aeea77c32e0f8c88121b31bf0f3c6f13143.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": "2dc0a6b9490c50cb656fe41b92ab39da3067e8ba0e1ee7c844c4e0fb6ee2be73", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57752d5ee4c16f62093c3883e66c6449dc039631e75dedd28b26f9647af5f50f", "generation_seconds_batch": 18.874524860992096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1474698781967163, "target_z": -0.42382811592606184, "ce": 6.24500846862793, "genuineness": 4.557555198669434, "identity": 0.7286542057991028, "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_Elation/2dc0a6b9490c50cb656fe41b92ab39da3067e8ba0e1ee7c844c4e0fb6ee2be73.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "2df4534c4cbe9330e80173a1b296036ed8ca8476afc617463a7f153f9e4a1f4a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "26d2f2678200cc99b8915e1c07eff6504055d1a23feb7c086f0603d4c09f19ea", "generation_seconds_batch": 21.70181178499479, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.214444398880005, "target_z": 2.4531248859276347, "ce": 5.95112943649292, "genuineness": 3.848362922668457, "identity": 0.6461980938911438, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2df4534c4cbe9330e80173a1b296036ed8ca8476afc617463a7f153f9e4a1f4a.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "2df53fa04f19b0584415c6cfcf7f19f31fbc14fb8df49c18004ea18d9c1990fa", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d444487d528e153e41f1f7a6fe553b075737a41f175568173dc837fd8a11fd4a", "generation_seconds_batch": 21.9697520469781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.041334629058838, "target_z": 0.8203124637042475, "ce": 6.133810997009277, "genuineness": 4.519899368286133, "identity": 0.7895046472549438, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2df53fa04f19b0584415c6cfcf7f19f31fbc14fb8df49c18004ea18d9c1990fa.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": "2e1283bafa58536f2146d02bdc63d26fc42a4e6d4f8f266b0f59283bc61c5784", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97796824e276c5a439a23517770220881ba9e85b5f9f9acb2b83f4a427d3cf43", "generation_seconds_batch": 21.779495792929083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9487206935882568, "target_z": 0.6914062111116936, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.6790835857391357, "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_Elation/2e1283bafa58536f2146d02bdc63d26fc42a4e6d4f8f266b0f59283bc61c5784.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": "2e3a823a0760fe8764ae7467e86e79ce54329329e41804143c49d215481d9ddd", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e319c274c4578d2a3ec96a413cd8d6dfdf4cfbd064505f268615192d460c727", "generation_seconds_batch": 23.95560122304596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1058838367462158, "target_z": 0.9101563562947039, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.6405932903289795, "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_Elation/2e3a823a0760fe8764ae7467e86e79ce54329329e41804143c49d215481d9ddd.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "2e5a17fdd80d79c58d4b60d6c0d30b1c7adc68be0e48dc664b6946547d6ce9a4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bdfb24507c46c12fb0139c29bc3315bddea6cd9f6289bf1ed12fbef525bc5db3", "generation_seconds_batch": 23.14547524799127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7059599161148071, "target_z": 0.3535155692600943, "ce": 6.300607204437256, "genuineness": 4.21237325668335, "identity": 0.4840969741344452, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2e5a17fdd80d79c58d4b60d6c0d30b1c7adc68be0e48dc664b6946547d6ce9a4.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "2eda74cb20001d8973ef4aa3519018b71fb2158ff6e72bb28df910b896a5f6b6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7bcd21a9c225605d6bd7c27dc5179314eb0ed61233cff62ecd7d81b3e41e1f39", "generation_seconds_batch": 21.387981179985218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0273022651672363, "target_z": 0.8007812837031988, "ce": 6.062326908111572, "genuineness": 4.093128204345703, "identity": 0.6260290145874023, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2eda74cb20001d8973ef4aa3519018b71fb2158ff6e72bb28df910b896a5f6b6.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": "2ef041521979bf445d4f0631c3e53635a5ca57e7826501fd9c174ee6e7aa522e", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3491d764b6a3ef8fa1e5cdedbd7a82f8c386ef903b949e41ac8eb1d3eb7e6190", "generation_seconds_batch": 21.779495792929083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8589133024215698, "target_z": 0.5664062940734138, "ce": 6.2767791748046875, "genuineness": 4.068024158477783, "identity": 0.3208782970905304, "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_Elation/2ef041521979bf445d4f0631c3e53635a5ca57e7826501fd9c174ee6e7aa522e.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "2f0385915ebd997ae2f9cc7a158d4dde807f9c2d45a0955816cc0188b8ec33b2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0a99dc580e58b7d1efb0187ea1013c8f0e0308f7494fca5b148d577dd4098a74", "generation_seconds_batch": 22.307883083005436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25972920656204224, "target_z": -0.2675780951856318, "ce": 6.181467056274414, "genuineness": 4.545003414154053, "identity": 0.572053074836731, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2f0385915ebd997ae2f9cc7a158d4dde807f9c2d45a0955816cc0188b8ec33b2.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "2f08dc5ba1cdc52367655c8ad6d4cacf0101e1a64de2e9d2893cce541458f205", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1ff782e9c6212984cedc5ef22f0924ef21575fde1d4e48e6dba51d5486742387", "generation_seconds_batch": 22.91102287301328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36988362669944763, "target_z": -0.1142578261109072, "ce": 6.24500846862793, "genuineness": 4.607763767242432, "identity": 0.5485376715660095, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2f08dc5ba1cdc52367655c8ad6d4cacf0101e1a64de2e9d2893cce541458f205.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "2f32da41a2840065959b83e8da10d08393143b8fbf6b6eae2de23c96d0789a17", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2ed3a8a7818dfb1475518ea9c6109e4fcc7245fe7fd7e17ec3de2f926bee0b25", "generation_seconds_batch": 23.369476519990712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9346883296966553, "target_z": 0.6718750311106451, "ce": 6.467403411865234, "genuineness": 3.8671910762786865, "identity": 0.45519062876701355, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2f32da41a2840065959b83e8da10d08393143b8fbf6b6eae2de23c96d0789a17.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "2ff412781df8fab4a9cba35e8f56cc865ebcf7ac6a98660d7c13d32f9ae785c5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1805d21a1201d5344881f8362879fc1f4e8358cb21406fe26210404b577a95ba", "generation_seconds_batch": 16.56249330402352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.932904005050659, "target_z": 3.4531248859276347, "ce": 6.038498878479004, "genuineness": 3.986435890197754, "identity": 0.531113862991333, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/2ff412781df8fab4a9cba35e8f56cc865ebcf7ac6a98660d7c13d32f9ae785c5.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "301e6bfdabcee86a58aadb3668b5b4e4dc63cc2bed599f983097a53a705fd21e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4bd3843abf7689a68c0a545d71c3af759aa8c18ee819474a467adf9a488c4948", "generation_seconds_batch": 21.85247058409732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8953975439071655, "target_z": 0.6171874948148925, "ce": 6.41180419921875, "genuineness": 4.068024158477783, "identity": 0.5715100765228271, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/301e6bfdabcee86a58aadb3668b5b4e4dc63cc2bed599f983097a53a705fd21e.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "30493cd22d4bdc80aa1934f69a240a1ae0254ae157b52bd53b6c3d2ac17831ac", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2caaf77cc31e9fe359568f454fb95c451de27645ef726a817f72d31e7dba7fae", "generation_seconds_batch": 21.460230006021447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9936244487762451, "target_z": 0.7539062525925537, "ce": 6.507116317749023, "genuineness": 4.362998008728027, "identity": 0.44668322801589966, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/30493cd22d4bdc80aa1934f69a240a1ae0254ae157b52bd53b6c3d2ac17831ac.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "306863b489102175517a51d7f4ca60503ad3e84d410e6a815f7d8445e5953b77", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a28ae90561c51c0d911bb176e4c89d4c1429e35cfb4b82a531a645cd5246e2e7", "generation_seconds_batch": 23.445243839058094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1965833306312561, "target_z": -0.35546873703723125, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.5191711187362671, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/306863b489102175517a51d7f4ca60503ad3e84d410e6a815f7d8445e5953b77.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "3079608bbb68a0ffb8fe4f208317144374ed1f8d1d31409edebe6a2464bcc7c1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "990044a947e75269d73925f02173a7e7062e0fec068e0bbc122e58502a720b10", "generation_seconds_batch": 17.00338365091011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4959847927093506, "target_z": 1.453124885927635, "ce": 6.1020402908325195, "genuineness": 4.168440818786621, "identity": 0.6360605955123901, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3079608bbb68a0ffb8fe4f208317144374ed1f8d1d31409edebe6a2464bcc7c1.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": "3220c5e3a56945378763d421dbc6652b1c4ad60e569593aa423f1c102aa3a001", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I wrote the number on the envelope.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "536e18d688d6fc9d7e5b8cd3ab89a8939958159d2240423d2021bc4a3b2aed18", "generation_seconds_batch": 17.6678274970036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7485682964324951, "target_z": 1.8046874533340325, "ce": 6.300607204437256, "genuineness": 3.9048471450805664, "identity": 0.5224783420562744, "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_Elation/3220c5e3a56945378763d421dbc6652b1c4ad60e569593aa423f1c102aa3a001.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "326c98fb2eb45061941431feeaf8917cbb437168888555266b0c3e7cd7c4632e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8b1b3779275327df8c636fa8001e784ce75b47b6eb70195ade253f491bc6d850", "generation_seconds_batch": 21.9587020999752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.237788438796997, "target_z": 1.09374997925957, "ce": 6.197352409362793, "genuineness": 4.331617832183838, "identity": 0.6019582748413086, "hypothesis": "J'ai trouvé la 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_Elation/326c98fb2eb45061941431feeaf8917cbb437168888555266b0c3e7cd7c4632e.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "32775f60243bd56d40155958c9ab16e5ffaac2e14717adfb93ad97108148e93d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "09ac7b59c09b6fa9dce2dbc3e58be13a31c4f645dc6078d00c58efd468d1ca5b", "generation_seconds_batch": 23.24921011494007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4530256986618042, "target_z": 0.0014648550924226747, "ce": 6.221180438995361, "genuineness": 4.469690799713135, "identity": 0.7716071605682373, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/32775f60243bd56d40155958c9ab16e5ffaac2e14717adfb93ad97108148e93d.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "328a5cf2e7703174f2a566954510803c0c28ec04ed6ff8bc6933a2ee4acb07e8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "241341f2a6fab41950331afa89a4d545bf9bf24283ab90f3ec2affe1b9e6a098", "generation_seconds_batch": 24.343300836044364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6812126636505127, "target_z": 1.7109373911127423, "ce": 5.649308204650879, "genuineness": 3.7291181087493896, "identity": 0.09038802236318588, "hypothesis": "Ik 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_Elation/328a5cf2e7703174f2a566954510803c0c28ec04ed6ff8bc6933a2ee4acb07e8.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "3321981a20ff3a8ac33c7e55d5b3d432bbe803d9189649e75c7d22709a91b14c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "463cd736df2d464a0086dc9500215b7d9cc58426105e2fd5ff2b6f4a9536fa8a", "generation_seconds_batch": 23.798191750072874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5417807102203369, "target_z": 0.125, "ce": 6.23706579208374, "genuineness": 4.293961524963379, "identity": 0.5328549742698669, "hypothesis": "Die Tür 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_Elation/3321981a20ff3a8ac33c7e55d5b3d432bbe803d9189649e75c7d22709a91b14c.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "332a150fef872a635dacbd15bbacb604ef3832b80b78d90c29a51b37cac17ad0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0d48efbc7bae2a2c5b46978ececfb0b6347be0e60bc230bf95c687b0ad420df4", "generation_seconds_batch": 16.241332683013752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5278782844543457, "target_z": 4.281249771855269, "ce": 5.621508598327637, "genuineness": 3.9676074981689453, "identity": 0.1445198506116867, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/332a150fef872a635dacbd15bbacb604ef3832b80b78d90c29a51b37cac17ad0.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "33af5fc9c1ac750c8b3657679d4facece025ee157764ac7619d18ac8d83ccf03", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "88fac3a6269b60d6263b18a4b2b1d92f08c52756991eb7588b6734a7cbc4a39f", "generation_seconds_batch": 16.997988477931358, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.539996385574341, "target_z": 2.90624985481699, "ce": 5.998785495758057, "genuineness": 4.2249250411987305, "identity": 0.43786734342575073, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/33af5fc9c1ac750c8b3657679d4facece025ee157764ac7619d18ac8d83ccf03.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "33dbbd37e4042817d8ec93f499ed2b9a8777fa534ecb31241f2efbaa5c7e5278", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6f828f47e54ba38afcce9e1191c12a594292a74fafd5b54eb87b21fbe14ed6b3", "generation_seconds_batch": 24.316846782923676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8027836084365845, "target_z": 0.48828124222233876, "ce": 6.157639026641846, "genuineness": 3.8546390533447266, "identity": 0.29808321595191956, "hypothesis": "The 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_Elation/33dbbd37e4042817d8ec93f499ed2b9a8777fa534ecb31241f2efbaa5c7e5278.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "33ee80a9c73537189c34fbd7abbc211c560869d4e70cfd1d05f1ff4358fc0e87", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "833187f6282ba5c283b17b73dbb16440b28c25714e98eb7b4f638932a5252ce9", "generation_seconds_batch": 16.97691905288957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7985738515853882, "target_z": 0.48242182185264804, "ce": 6.229123115539551, "genuineness": 4.168440818786621, "identity": 0.7288497686386108, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/33ee80a9c73537189c34fbd7abbc211c560869d4e70cfd1d05f1ff4358fc0e87.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "4a35683ab4bbd6114982ea3f6cadfb2ac0c6ed808f945c29b0b2d02213eb81bb", "generation_seconds_batch": 15.260823262040503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15448608994483948, "target_z": -0.41406248444467747, "ce": 6.165581703186035, "genuineness": 4.293961524963379, "identity": 0.8712401986122131, "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_Elation/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.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": "33fb742f01c82c1899a3f4febc8b14cf447ec34db8dafeda13c82d697e7c9f45", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18bb165fda81543c00a0714145faa9f21250c9812d4c0e4948a1384d4a99ac22", "generation_seconds_batch": 22.210163590032607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.214444398880005, "target_z": 2.4531248859276347, "ce": 6.435632705688477, "genuineness": 4.2751336097717285, "identity": 0.5578593611717224, "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_Elation/33fb742f01c82c1899a3f4febc8b14cf447ec34db8dafeda13c82d697e7c9f45.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "d4a94abe7e43b9856909a39fb28b517b7a51affd7277861c05e717bdb370abb3", "generation_seconds_batch": 17.08410511096008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03100082278251648, "target_z": -0.5859375155553225, "ce": 6.3641486167907715, "genuineness": 4.086852550506592, "identity": 0.12011998891830444, "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_Elation/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "34d437ae89d7095f39669570ac7ee030ea0ad2132e79df9cded0fb801dee5d21", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9f9cf412229a55e693737ab65b2606aba045a0efebfe513adc860321e4f3420b", "generation_seconds_batch": 16.97173994302284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3937387466430664, "target_z": -0.0810546790742003, "ce": 6.292664527893066, "genuineness": 4.149612903594971, "identity": 0.49217015504837036, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/34d437ae89d7095f39669570ac7ee030ea0ad2132e79df9cded0fb801dee5d21.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "358ae12a44495f8504bcdb8a4b916c4482cbda73216857ab3ac9ae9f62d3dc0e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "08f53b236424af5e99c60599620cedc5de46f9bd08a3d6f203390bb0af269cff", "generation_seconds_batch": 16.814932734007016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3219828605651855, "target_z": 1.2109373911127423, "ce": 5.831989288330078, "genuineness": 3.760498285293579, "identity": 0.48111891746520996, "hypothesis": "The 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_Elation/358ae12a44495f8504bcdb8a4b916c4482cbda73216857ab3ac9ae9f62d3dc0e.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": "3622ae876a890fe49808cdcdb41af96222a8dfd4b21fbc3d6bdfe5159c43bda1", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "efee04370e8b57ce7ff98c6785d1109ec1532cd0ab8a59e74ed4e1b2492c7ceb", "generation_seconds_batch": 16.73858942592051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5344136953353882, "target_z": 0.11474609731476142, "ce": 6.284721851348877, "genuineness": 4.143336772918701, "identity": 0.47265130281448364, "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_Elation/3622ae876a890fe49808cdcdb41af96222a8dfd4b21fbc3d6bdfe5159c43bda1.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": "36447b9425cc2c7e831524736355a282d2a28ac26f69e218e480cb3d3e467a91", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2223f008564b2fd4719fe4a733ac23d33d733035544c4a95ec725347bf942ea4", "generation_seconds_batch": 21.40774776902981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9739790558815002, "target_z": 0.7265624844446775, "ce": 6.086154937744141, "genuineness": 4.18099308013916, "identity": 0.5752049088478088, "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_Elation/36447b9425cc2c7e831524736355a282d2a28ac26f69e218e480cb3d3e467a91.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "36588550ab04eed48791e2e290c99562f20dc68bb9c386d6ae75ca2f9156d868", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5f6acc59ed14b2ef7a3a3706292a9f46aca7f037c1ce0ee690865efe9ba8b050", "generation_seconds_batch": 26.74647353508044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.068507432937622, "target_z": 2.25000008296172, "ce": 5.661221981048584, "genuineness": 3.986435890197754, "identity": 0.6378633975982666, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/36588550ab04eed48791e2e290c99562f20dc68bb9c386d6ae75ca2f9156d868.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "3682789dbc6fda2f42a6f9b555044bbe79fe32db4ec6511060b45c62c485dc71", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ea6dc82c1b90314c8577fc2cc4388078f812bed214e0dc563329c2987f018d7a", "generation_seconds_batch": 22.054989090072922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.562448263168335, "target_z": 2.9374998755574198, "ce": 5.287916660308838, "genuineness": 3.8169827461242676, "identity": 0.08776185661554337, "hypothesis": "De deur 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_Elation/3682789dbc6fda2f42a6f9b555044bbe79fe32db4ec6511060b45c62c485dc71.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "3708a93f6b15597e13e3e37ef609d0205a075fe4d2ea01dba90fe441451af263", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b1d7681f82284c7afef67d5b7f150dde44060ac11d8c053005f07be9bf145261", "generation_seconds_batch": 23.946009433013387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.372499704360962, "target_z": 1.2812501037021502, "ce": 6.332377910614014, "genuineness": 4.300237655639648, "identity": 0.29273635149002075, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3708a93f6b15597e13e3e37ef609d0205a075fe4d2ea01dba90fe441451af263.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "37a35c4be681123c7fb1ab4d33d4530f4d289f7d8e1f6bccf154ae599fd4c041", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cc130a069a56a0816eda4c76d27a01df573544f4b6059d7260ba7d7239a25eb4", "generation_seconds_batch": 22.108214321080595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6634817123413086, "target_z": 3.078124968889355, "ce": 5.216432571411133, "genuineness": 3.5439748764038086, "identity": 0.020564913749694824, "hypothesis": "De deur staat nog open! Ik heb je jaas 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_Elation/37a35c4be681123c7fb1ab4d33d4530f4d289f7d8e1f6bccf154ae599fd4c041.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "38219ba07cbc963b9300d948b5113ca51fb51b68c7e6bb0c876ef674b8d7f5d6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "013f85624ce8f1ace54e2833f8039c8840f648b6068f78d5d651c0f1f47538cf", "generation_seconds_batch": 22.781430372036994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1695406436920166, "target_z": 2.3906248444467746, "ce": 6.046441555023193, "genuineness": 3.6914620399475098, "identity": 0.2879176139831543, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "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_Elation/38219ba07cbc963b9300d948b5113ca51fb51b68c7e6bb0c876ef674b8d7f5d6.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "384829404ccdc0ab9610adde52da842cd48026a51cd5807dc7485e11153a67d6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ca670ab654d92a789823cc428157491111d2a862917d8878cdcc9146732895d7", "generation_seconds_batch": 22.163064071093686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5438855886459351, "target_z": 0.12792971018484536, "ce": 6.133810997009277, "genuineness": 4.425758361816406, "identity": 0.7812924385070801, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/384829404ccdc0ab9610adde52da842cd48026a51cd5807dc7485e11153a67d6.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "38f08c9e5ed040482eda0d7de675603df43d06e3f6f4bc90c9a316b5630670eb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8df6d6f5c3f1b8d65adcabe00214fba42eea8ad92f60cba8028b3f4c6f7bfaa9", "generation_seconds_batch": 22.954179021995515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3051440715789795, "target_z": 1.18750004148086, "ce": 6.403861999511719, "genuineness": 4.105680465698242, "identity": 0.5893088579177856, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinstehen.", "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_Elation/38f08c9e5ed040482eda0d7de675603df43d06e3f6f4bc90c9a316b5630670eb.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": "38fefa4c238772a9f150b93481e00c331b04230f67e54ecfd55fe1eb3e603c3c", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "413aaed24e58baf897aa85464d5128f989b03df963247be4209b46c927fc1559", "generation_seconds_batch": 24.078296349034645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7340247631072998, "target_z": 0.3925780951856318, "ce": 6.252951145172119, "genuineness": 4.20609712600708, "identity": 0.5226913690567017, "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_Elation/38fefa4c238772a9f150b93481e00c331b04230f67e54ecfd55fe1eb3e603c3c.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "395b978efda0817a62f9cbd7c00bb74cbf70a2ab9bbaac09ca07008a4bb0ae9c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "64692e218f9f248b427e88c29f1a046d66b244e1fbce373afb68930ea65dc0d0", "generation_seconds_batch": 21.96396826801356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3033597469329834, "target_z": 3.96874989629785, "ce": 5.685050010681152, "genuineness": 4.017816066741943, "identity": 0.6245965957641602, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/395b978efda0817a62f9cbd7c00bb74cbf70a2ab9bbaac09ca07008a4bb0ae9c.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "39671628ee28282b8c44f00f058795c70896842f5275576d550d77031db99ecc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "908001954e41604d492350c58bf306aab9f969ed8693039eaf176bf91393b65b", "generation_seconds_batch": 22.665447785984725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36567389965057373, "target_z": -0.12011720499973784, "ce": 6.229123115539551, "genuineness": 4.68307638168335, "identity": 0.4844279885292053, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/39671628ee28282b8c44f00f058795c70896842f5275576d550d77031db99ecc.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "39b196b9404dcf41852540a2142fea2d09c22e012081de7e000fad96830c5860", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b6e47462790d483af6242c1f3c9b2a66c1d57061c8b3e6f7bd117d9da7e20aec", "generation_seconds_batch": 22.708817503065802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8252354860305786, "target_z": 0.5195312629627687, "ce": 6.23706579208374, "genuineness": 4.13078498840332, "identity": 0.5777449011802673, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/39b196b9404dcf41852540a2142fea2d09c22e012081de7e000fad96830c5860.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "39b2f459e2dc0a9cc848be57533ca0d2c7876949786d19fe2ea4db642dec719f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "67ad6b310a602a0811f7eba55a47666d1d09c4633997431c4b52894aeac02d4c", "generation_seconds_batch": 27.550083438982256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9899258613586426, "target_z": 2.140625010370215, "ce": 6.0305562019348145, "genuineness": 4.300237655639648, "identity": 0.4882088303565979, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/39b2f459e2dc0a9cc848be57533ca0d2c7876949786d19fe2ea4db642dec719f.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "39e7e82f0d6c296dea81bd6406ca9e090e4a60eae81cdddc8e8849d217615ead", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "98f650b407632a4e5eaca859c5f741bd0dc7fa440d43373a34e46ac468cb907d", "generation_seconds_batch": 17.09765798598528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4903719425201416, "target_z": 1.4453125466659675, "ce": 6.308549880981445, "genuineness": 4.482243061065674, "identity": 0.516643762588501, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/39e7e82f0d6c296dea81bd6406ca9e090e4a60eae81cdddc8e8849d217615ead.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "3a6ba77a2583a951cf73711016e8f6ad230d964b91c9614b2adf98288a9750fe", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "af72bc6c0a21ae466d0d7861e325ed7b1b4a24be514d72392fdfee293a4e6eba", "generation_seconds_batch": 22.992220995016396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5958055257797241, "target_z": 0.20019534166622974, "ce": 6.292664527893066, "genuineness": 4.105680465698242, "identity": 0.20188413560390472, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3a6ba77a2583a951cf73711016e8f6ad230d964b91c9614b2adf98288a9750fe.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "3abbc3d87a0247f1268918c9f0e827d0642896f890e445a8ca50a9e22cd264f6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cfd5620c84f97fab706ec54e66d98d1d1b3f8cab4c01115fd1a9f549d8a2b5ad", "generation_seconds_batch": 17.232418443076313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3668866157531738, "target_z": 1.2734374325936024, "ce": 5.990842819213867, "genuineness": 3.578493118286133, "identity": 0.5410134792327881, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3abbc3d87a0247f1268918c9f0e827d0642896f890e445a8ca50a9e22cd264f6.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "3ad9f8f29a1a9b58849ffe3bd3958f73f15f61225308349eb9819a0898ef5b15", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "67f3ed4322573377c7bdccc89b3c6f989c0ee841cae11bf67ac3dbb246efdde2", "generation_seconds_batch": 24.31933836801909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5914053916931152, "target_z": 1.5859376399979028, "ce": 6.38797664642334, "genuineness": 3.9299514293670654, "identity": 0.5276179909706116, "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_Elation/3ad9f8f29a1a9b58849ffe3bd3958f73f15f61225308349eb9819a0898ef5b15.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "3b2ce14745a33683ebfec126520b0e2b516c0f99276a174953b83c303ae990a6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "43c2ac7b56f809cdb71cb4cc8bb041e13f4c93c5483f50993034661699181c24", "generation_seconds_batch": 20.54833714396227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.719611406326294, "target_z": 3.15625002074043, "ce": 5.700935363769531, "genuineness": 3.722842216491699, "identity": 0.7391993999481201, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3b2ce14745a33683ebfec126520b0e2b516c0f99276a174953b83c303ae990a6.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "3b30a61b7afdefb5710c97baecc89bdfed7505d14d79ed638493ccdf3442ecae", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a4000757bae677f7544da98680ebc0769c359dd9c2b556d8541d225093ece690", "generation_seconds_batch": 15.955135722993873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6807016134262085, "target_z": 0.31835937888883065, "ce": 6.23706579208374, "genuineness": 4.432034492492676, "identity": 0.720048189163208, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3b30a61b7afdefb5710c97baecc89bdfed7505d14d79ed638493ccdf3442ecae.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "3b4746dd8de7fa555a6e3eae7a6f5cf6a871a86782b5e367de7dbbabb4f53d99", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "52922ae86a29b34200f378c5deca148a60ca12c844e76522b8067ace788cc8a2", "generation_seconds_batch": 23.069029836100526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5112602114677429, "target_z": 0.08251953416662297, "ce": 6.205295085906982, "genuineness": 4.557555198669434, "identity": 0.6548354625701904, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3b4746dd8de7fa555a6e3eae7a6f5cf6a871a86782b5e367de7dbbabb4f53d99.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "3b4db841654069cc938442d3c96b586a0b341743b9a2d86580b4cdea37f3d2c3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fc0369d1014cea5bec35f88cdd072f11fb96988db4c03a75dece13e2220b2d44", "generation_seconds_batch": 19.244884423096664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.532659649848938, "target_z": 0.11230469981463033, "ce": 6.23706579208374, "genuineness": 4.105680465698242, "identity": 0.2892856001853943, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3b4db841654069cc938442d3c96b586a0b341743b9a2d86580b4cdea37f3d2c3.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": "3b5c7b301b01a7cccacd1bd51bf0f117390db0884502a43284b8b2f67cde9d07", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f47e534172991f495b4bcb0bb47e4ce4c0effbbd2267dfa9143d0b3a1d856cfa", "generation_seconds_batch": 18.153539462946355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7887511849403381, "target_z": 0.46874997925956996, "ce": 6.340320587158203, "genuineness": 4.13078498840332, "identity": 0.6051256656646729, "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_Elation/3b5c7b301b01a7cccacd1bd51bf0f117390db0884502a43284b8b2f67cde9d07.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "3bc29af6fcc37b2ec87ce7cec5b367d5f24223f58112f7210d63db2c546087d9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f0ab6a89cf4d7e53fd233abc57a60a7aa15bdd15c5822300e10775d89a24fc15", "generation_seconds_batch": 25.505774015909992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1760458946228027, "target_z": 1.0078125881468276, "ce": 6.332377910614014, "genuineness": 4.3127899169921875, "identity": 0.295134574174881, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3bc29af6fcc37b2ec87ce7cec5b367d5f24223f58112f7210d63db2c546087d9.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "3be8a07581967999b5d96d46b0cf1509c5c0d27a5f737a855702b09245afac76", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "047edd62fecfb7fbd0fbf0189338f8649b77341b63689f4c28f4df315f24421c", "generation_seconds_batch": 22.91102287301328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5193288326263428, "target_z": 0.09374997925956996, "ce": 6.141753673553467, "genuineness": 4.1998209953308105, "identity": 0.626726508140564, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3be8a07581967999b5d96d46b0cf1509c5c0d27a5f737a855702b09245afac76.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "d6c6d224ef05e1a681dc5530af59d18cdbc710ebf03fae810cc433ddcffa1164", "generation_seconds_batch": 15.781331780017354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2372773289680481, "target_z": -0.29882811592606184, "ce": 6.181467056274414, "genuineness": 4.325342178344727, "identity": 0.6249862909317017, "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_Elation/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.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": "3d217981d82f62381141c727cad18e9e197fbe150072ffda22a6908ae92ebc4b", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fdfb2da04b4c64117898d16d294587e739f2176f47be4b901933f6378eaf946", "generation_seconds_batch": 15.244649747037329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.553006649017334, "target_z": 0.14062501037021502, "ce": 6.157639026641846, "genuineness": 3.9550557136535645, "identity": 0.46207916736602783, "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_Elation/3d217981d82f62381141c727cad18e9e197fbe150072ffda22a6908ae92ebc4b.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "3db9ebeb7790a6f38972bc1e00bba5272c4c5bd3bbccfb483383626d1a993b85", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f7799bce6c55a24c3c8037fb6befdb4dc1dd27489187a876cf1a986314630101", "generation_seconds_batch": 16.925982574932277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4631991982460022, "target_z": 0.015625010370215017, "ce": 6.260893821716309, "genuineness": 4.2374773025512695, "identity": 0.36911553144454956, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3db9ebeb7790a6f38972bc1e00bba5272c4c5bd3bbccfb483383626d1a993b85.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "3dc983ee3cdc515cbd4d5b51db032bafb8d3f9d94f9dd6bed17d71e55294e793", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0ea132855c068d0bfba4a82075bbae2bdd987aaec33d89b3af6160600102cb0f", "generation_seconds_batch": 23.696735656936653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.730837345123291, "target_z": 3.171875031110645, "ce": 6.022613525390625, "genuineness": 4.005263805389404, "identity": 0.703378438949585, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3dc983ee3cdc515cbd4d5b51db032bafb8d3f9d94f9dd6bed17d71e55294e793.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": "3e478c6b39f6309c9dbc14c0183605b5014c6b7e9ab11e6ea8b5800453aa2770", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "905848e0b3733494eeeb7344bdf5266783025dee77bdacbe7a03c666f12d2dde", "generation_seconds_batch": 19.62183290894609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36637553572654724, "target_z": -0.11914062111116937, "ce": 6.125868320465088, "genuineness": 4.268857479095459, "identity": 0.6356098651885986, "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_Elation/3e478c6b39f6309c9dbc14c0183605b5014c6b7e9ab11e6ea8b5800453aa2770.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "3e8c6bac9469dc4ea95bad53dbf07dd608cb0d472136561d8a14e16cdcbba262", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7d9747407afe1c91e9d781446487c11eeb6043a99cf9dca3d5eb50b30455eec4", "generation_seconds_batch": 23.670831549097784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1816587448120117, "target_z": 1.015624927408495, "ce": 5.982900142669678, "genuineness": 4.055472373962402, "identity": 0.24072426557540894, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3e8c6bac9469dc4ea95bad53dbf07dd608cb0d472136561d8a14e16cdcbba262.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "3f526df5daa405ecaaf29bf3a9a9e8899a4c0165b69750860ecf4076eea861b2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c13f023ecbac94c5db27516ae0965d8349f07ce99f4b74041235956b5ca99794", "generation_seconds_batch": 23.059506459976546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.079733371734619, "target_z": 2.265625093331935, "ce": 5.831989288330078, "genuineness": 3.5973212718963623, "identity": 0.3932787775993347, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/3f526df5daa405ecaaf29bf3a9a9e8899a4c0165b69750860ecf4076eea861b2.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "3f59f297ccf2a2e4edff8b7611893e7f775b6838cb47c89a72a075f0f117dc51", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3c9c74a28169750e6a606b185b049cf1ace3247883c8b4795c56dd60d1cd8ccb", "generation_seconds_batch": 22.71909558097832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7578798532485962, "target_z": 0.4257812007414787, "ce": 6.046441555023193, "genuineness": 3.7416701316833496, "identity": 0.3487667143344879, "hypothesis": "The 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_Elation/3f59f297ccf2a2e4edff8b7611893e7f775b6838cb47c89a72a075f0f117dc51.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "3fe43d556faceaeecbd4cbb1f43aaf145abf1bb395b6e4a1824a534bfe6652a8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0ca172bfb251a94912a0688eab7c414c13c03733be9e61169014c12d77c018bd", "generation_seconds_batch": 18.025433639995754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41268250346183777, "target_z": -0.05468749481489249, "ce": 6.062326908111572, "genuineness": 3.873466968536377, "identity": 0.47817403078079224, "hypothesis": "The 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_Elation/3fe43d556faceaeecbd4cbb1f43aaf145abf1bb395b6e4a1824a534bfe6652a8.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "402c87ce72ee66edf5f91449cf0bd52b0bed65be8cf639297b068eb1124f9643", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "22ecd8e21f3d859068f53ded6e1f52489d7715fb52a5e75c735a048d140643e4", "generation_seconds_batch": 17.78173051297199, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2490143775939941, "target_z": 1.109374989629785, "ce": 5.935244083404541, "genuineness": 3.8044304847717285, "identity": 0.45765048265457153, "hypothesis": "De deur 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_Elation/402c87ce72ee66edf5f91449cf0bd52b0bed65be8cf639297b068eb1124f9643.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": "4042cb5dd9a4cb5c73f103f7ec81ca4b0495acca97754a21e823bb4b5087f1e0", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "230760c77c41e7c2282b049769e35bf53fdec2fe6ac3c6f1e67dadf53866c39b", "generation_seconds_batch": 23.4551556709921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4623069763183594, "target_z": 1.4062498548169897, "ce": 6.078212261199951, "genuineness": 4.457139015197754, "identity": 0.6238514184951782, "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_Elation/4042cb5dd9a4cb5c73f103f7ec81ca4b0495acca97754a21e823bb4b5087f1e0.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": "4074ee41932282ede3330550c74d554930e759e74a738b1e453d8344036af0a6", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91266475b10ca6d3526d145d138f62ca0b5786f00a15dddd9b31988e2a365ce5", "generation_seconds_batch": 23.843906031921506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0806254148483276, "target_z": 0.875, "ce": 5.935244083404541, "genuineness": 4.042920112609863, "identity": 0.3831363618373871, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk in de la en daarna, naast het raam. Neem ze mee als je weggaat!", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4074ee41932282ede3330550c74d554930e759e74a738b1e453d8344036af0a6.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": "41777bd7f548c6c9a38f1f9eb10da55883335e1791cbdb7bd8b4f836f4915f18", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e773829a623ac77047293355df90499f1aa27a9efa361d53ef29cef6daf690d3", "generation_seconds_batch": 21.418959315982647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6812126636505127, "target_z": 1.7109373911127423, "ce": 6.1020402908325195, "genuineness": 4.1998209953308105, "identity": 0.44144341349601746, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, le bien and verify the two dernier chiffres. Appelle moi quand tu auras un moment.", "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_Elation/41777bd7f548c6c9a38f1f9eb10da55883335e1791cbdb7bd8b4f836f4915f18.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": "41ac7d3005a42ba877fab3ae7097666228d160b25b29184f39299a5338212ea4", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34aec6673e56a87a62d5965a7791acd779a5b9457ee8b1e46269f64eb0045399", "generation_seconds_batch": 15.258758691954426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.057281494140625, "target_z": 2.2343750725915053, "ce": 6.419747352600098, "genuineness": 4.507347106933594, "identity": 0.6081221699714661, "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_Elation/41ac7d3005a42ba877fab3ae7097666228d160b25b29184f39299a5338212ea4.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "41bce9318d7f1a156253712074f8b6e37c2caac31020ece9778cd41db0048788", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bbee65e23d85ae4d939023b86b0152d01e01f20c6d05bc74a0d6c5dc9e4612dd", "generation_seconds_batch": 16.4094361619791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5438855886459351, "target_z": 0.12792971018484536, "ce": 5.927301406860352, "genuineness": 4.099404335021973, "identity": 0.2838393747806549, "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_Elation/41bce9318d7f1a156253712074f8b6e37c2caac31020ece9778cd41db0048788.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "7d8e267757b641a3af11749b2ef9ad99612ea3da1f664b098220eb58d1a8bedc", "generation_seconds_batch": 15.260823262040503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1348406970500946, "target_z": -0.4414062525925537, "ce": 6.173524379730225, "genuineness": 4.369274139404297, "identity": 0.553236722946167, "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_Elation/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.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": "435d512716e959697a87f80c464e7699b773edf7f9eccfbb656bc56b6b096f39", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53a30b1a9b6a76c29b606fe0e29bf6a1893f9681aaf5d1f57380ad9ba636646f", "generation_seconds_batch": 21.28363686101511, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3270847797393799, "target_z": -0.17382811592606187, "ce": 6.316492557525635, "genuineness": 4.193545341491699, "identity": 0.4675135612487793, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/435d512716e959697a87f80c464e7699b773edf7f9eccfbb656bc56b6b096f39.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ef8d956db64447f4077d19dc222f6fd5a15c1edfe357dcba0101fe7ec11f9ad6", "generation_seconds_batch": 21.021047381917015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18676063418388367, "target_z": -0.36914062111116935, "ce": 6.213237762451172, "genuineness": 4.595211505889893, "identity": 0.6122995615005493, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "447a82ee363e80b9a5db64371f90dd7a01ac6f3fbf28767af20b4858a1b9de6b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cf9229d304d808e7ff29701ebd019608f7ecda5a10f9b88d068d59d6e67379ac", "generation_seconds_batch": 22.040336080943234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6610562205314636, "target_z": 0.29101561074095433, "ce": 6.09409761428833, "genuineness": 4.174716949462891, "identity": 0.6858833432197571, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/447a82ee363e80b9a5db64371f90dd7a01ac6f3fbf28767af20b4858a1b9de6b.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "44bf6027e2a14a6465c6019fe33a16d1960ccb996763dd43d013049790e14d85", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b3abac7b0be00b6f4ca3063832467e8ffa29570dfad1fe4ccc11b3a8c975870c", "generation_seconds_batch": 23.43631756096147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3355042338371277, "target_z": -0.1621093581484006, "ce": 6.205295085906982, "genuineness": 3.9676074981689453, "identity": 0.7112132906913757, "hypothesis": "La porte 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_Elation/44bf6027e2a14a6465c6019fe33a16d1960ccb996763dd43d013049790e14d85.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": "44ec125b142441de1922c17ecb36a510e4b4b14f615f964b13dad11d1e6108d2", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51df3164403fb4df80dfccba13659b2f3ff358dde6710f21a3c2f3d6043f8410", "generation_seconds_batch": 22.753808113047853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9234623908996582, "target_z": 0.65625002074043, "ce": 6.09409761428833, "genuineness": 4.068024158477783, "identity": 0.4692775011062622, "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_Elation/44ec125b142441de1922c17ecb36a510e4b4b14f615f964b13dad11d1e6108d2.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": "45268b6aa80fb7776136008c6b2d134dedb8bb02ca43af2f3369945f0d65e427", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Someone moved the little blue chair.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae0bec78ad45a415e5fee54da7f00ba5bb83326cb3995255f92603caadbb547c", "generation_seconds_batch": 20.75479608005844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1881638765335083, "target_z": -0.3671874948148925, "ce": 6.38003396987915, "genuineness": 4.256305694580078, "identity": 0.41951483488082886, "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_Elation/45268b6aa80fb7776136008c6b2d134dedb8bb02ca43af2f3369945f0d65e427.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "452ff9b7a63225687ab25a70fedd238a7344233fe81b41572c5e144075d28c7f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4508ef8a8a0f07f60847f1814fbeca380da4ae51ecde1bd619be2e7f462ece71", "generation_seconds_batch": 20.965210031019524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6428140997886658, "target_z": 0.265625010370215, "ce": 6.157639026641846, "genuineness": 4.231201171875, "identity": 0.7557619214057922, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/452ff9b7a63225687ab25a70fedd238a7344233fe81b41572c5e144075d28c7f.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "455a8d2f5b4eb4d8ad43e019cba7471ca1b6b22abea370df60b8eb274bb43e69", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "72d6081b57f6723251a5938529df89df433558868a0f43f21de4acce8d75058d", "generation_seconds_batch": 17.9664074620232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3207702040672302, "target_z": -0.18261716351887777, "ce": 6.252951145172119, "genuineness": 4.344170093536377, "identity": 0.5771803855895996, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/455a8d2f5b4eb4d8ad43e019cba7471ca1b6b22abea370df60b8eb274bb43e69.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "dc365a4b91fbcefa94979d210f0c12b557bbd438ea68e33bc47314a6b68ce79b", "generation_seconds_batch": 16.163655983982608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0730980634689331, "target_z": -0.5273437681478763, "ce": 6.4515180587768555, "genuineness": 4.381826400756836, "identity": 0.6040276288986206, "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_Elation/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "45fce62798346a1d9d634e2e91a84b31912cbcf4bbab10c986722bdf4ae890dc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2b15f123195bb1d802783473dadbb43837344c67555d0144fdddf52de4886e9a", "generation_seconds_batch": 22.970760873053223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0693994760513306, "target_z": 0.859374989629785, "ce": 6.221180438995361, "genuineness": 4.005263805389404, "identity": 0.39558565616607666, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/45fce62798346a1d9d634e2e91a84b31912cbcf4bbab10c986722bdf4ae890dc.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "47650ae8c66db604fed439bf3c4123380b73802c9e0245984d44eb397e569a8e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5c1bcca3b3371c39f0b7b3b2335e8a72a9d2c769b382644d035085f1fee8b80f", "generation_seconds_batch": 18.562913847970776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.090067148208618, "target_z": 3.671875031110645, "ce": 5.403085231781006, "genuineness": 3.6098732948303223, "identity": 0.5310096144676208, "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_Elation/47650ae8c66db604fed439bf3c4123380b73802c9e0245984d44eb397e569a8e.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "47791dc84c2fb16ad97377f3890fa8c390a0382b5710918b6353cce4dedf3b59", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "85ddd9c3b604249cd8a703242d30b6994e232c89edb0230a346893945e1eeb30", "generation_seconds_batch": 21.238748879986815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4800380766391754, "target_z": 0.03906248444467748, "ce": 6.268836498260498, "genuineness": 4.319066047668457, "identity": 0.6966021656990051, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen 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_Elation/47791dc84c2fb16ad97377f3890fa8c390a0382b5710918b6353cce4dedf3b59.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "47951118d15591b50e5bafe910b5a790e5c552393296a036093341aa0638e53b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6164b62d1e7fb27c883b0ec8a819a11a2cbe9357b88d9d6d41afb550b91d53f5", "generation_seconds_batch": 20.71985728002619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7817350029945374, "target_z": 0.45898438925904567, "ce": 6.133810997009277, "genuineness": 4.011539936065674, "identity": 0.7053130865097046, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/47951118d15591b50e5bafe910b5a790e5c552393296a036093341aa0638e53b.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": "47b09d10c91c0d59e0d5a8d22d052ab71f334784bdb3b1b49256548ffab6e028", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Your message arrived after I had left.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85adbd9e67d3ef486c150c83145dadb082838842be90cc1299b60202a0e09b27", "generation_seconds_batch": 22.064946958096698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17693793773651123, "target_z": -0.3828125051851075, "ce": 6.38003396987915, "genuineness": 4.111956596374512, "identity": 0.29652562737464905, "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_Elation/47b09d10c91c0d59e0d5a8d22d052ab71f334784bdb3b1b49256548ffab6e028.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "8e0466d8fb566c4201ca010553ebf617efcc3714f12cfbc00457be3454aed251", "generation_seconds_batch": 17.780143831972964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1222115159034729, "target_z": -0.45898438925904567, "ce": 6.062326908111572, "genuineness": 4.331617832183838, "identity": 0.839515745639801, "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_Elation/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "48b989b824b6acaf7aa1c9b0d74126979c40183d844e7b6c235bd0b8558ab17d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9e5d858d622375407bae6c3989fc66e45efc4533a07dad1ab43e442f612ed509", "generation_seconds_batch": 21.99179253494367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4505700170993805, "target_z": -0.001953126296276877, "ce": 6.24500846862793, "genuineness": 4.331617832183838, "identity": 0.6387181282043457, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/48b989b824b6acaf7aa1c9b0d74126979c40183d844e7b6c235bd0b8558ab17d.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "49327ee6ec585d37ce55a98fd9ff8842a15b773dcaa062bf65042d2a775a0d95", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7f4443df6b98d55e49603d8687e4a78c59d6bdc90b4c1da28b32bc80d532b746", "generation_seconds_batch": 17.837215775973164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8112030625343323, "target_z": 0.5, "ce": 6.006728172302246, "genuineness": 4.118232727050781, "identity": 0.4276540279388428, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/49327ee6ec585d37ce55a98fd9ff8842a15b773dcaa062bf65042d2a775a0d95.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": "4979029a235bdc69c38e1b0df0b97bc1df1286bc027392d07f82103c93ab20a9", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cbc84dc63745af64299df3b7dda4f291d26b4c87d241e5ed0a722d87efbdeca", "generation_seconds_batch": 16.90012120793108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25551944971084595, "target_z": -0.27343751555532253, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.8413134217262268, "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_Elation/4979029a235bdc69c38e1b0df0b97bc1df1286bc027392d07f82103c93ab20a9.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "497b73dea476370892bbac6e155ce6484dad48fff38f70bf13a765621005dc4c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "018c2db99422b10d881c6792c3d45cf0589a37cc07c1aaef53ee8cbf317de879", "generation_seconds_batch": 18.591767744044773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3612737655639648, "target_z": 1.265625093331935, "ce": 6.125868320465088, "genuineness": 4.394378662109375, "identity": 0.7353360056877136, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/497b73dea476370892bbac6e155ce6484dad48fff38f70bf13a765621005dc4c.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "49c6ccaaf092695c6cc069e5e2d004c1bdeb9fc804b9909f2a88537ec1d7c873", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "80e18ad09cacf3bf91e7994cf6b413244da302082fd53509fe4ace4c2cf95780", "generation_seconds_batch": 24.14089886203874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7822461128234863, "target_z": 1.8515624844446774, "ce": 5.816103935241699, "genuineness": 3.9048471450805664, "identity": 0.5827319025993347, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/49c6ccaaf092695c6cc069e5e2d004c1bdeb9fc804b9909f2a88537ec1d7c873.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": "49c9da9fbbaa4538c28a7899aa87cd028412777747de36f15aa7839e28871a0a", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "991161b43654993b9dd3523720cf676067c3e9f61192fd64ec492df6fa8966c3", "generation_seconds_batch": 26.622751284041442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6755998134613037, "target_z": 1.703125051851075, "ce": 6.1020402908325195, "genuineness": 3.9550557136535645, "identity": 0.6130822896957397, "hypothesis": "Ik schreef de nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd.", "wer": 0.08695652173913043, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/49c9da9fbbaa4538c28a7899aa87cd028412777747de36f15aa7839e28871a0a.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "08551474ad287b3072e6912fda100f92c40a4941796369db4818de854d391111", "generation_seconds_batch": 19.258722561993636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33339935541152954, "target_z": -0.16503906833324594, "ce": 6.149696350097656, "genuineness": 4.143336772918701, "identity": 0.7345861196517944, "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_Elation/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "49d53aa235b5edbf0732a635ed0d5f3a8abc7f017270f33fb274f65ceab4b674", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 130, "seconds_generated": 10.4, "mp3_sha256": "795b85e85534fecc9c5506cb728739ea9f63dd982f6978f0e0dc894e66c830e8", "generation_seconds_batch": 24.192724611028098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.572782039642334, "target_z": 4.34374981333613, "ce": 5.248203277587891, "genuineness": 3.7793264389038086, "identity": 0.3364402651786804, "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_Elation/49d53aa235b5edbf0732a635ed0d5f3a8abc7f017270f33fb274f65ceab4b674.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "4a01c54d1ea057654db84df7262ff1962f29c0a6aca5a3ac5f26be0fd23d3f3a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "467cf89d328a188067f3255e9171f3673a9730cc7e61fce82d148d7156a0b001", "generation_seconds_batch": 25.25397293397691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9571401476860046, "target_z": 0.7031249688893549, "ce": 5.375286102294922, "genuineness": 3.550251007080078, "identity": 0.36786913871765137, "hypothesis": "The 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_Elation/4a01c54d1ea057654db84df7262ff1962f29c0a6aca5a3ac5f26be0fd23d3f3a.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "4a5526b47802c798590cd64c30fdec88d3a27889c6367585c6678d9903f4273f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b4c42e306e713f67deee387bf8318fd638acfec3727f5f864315c2149523f937", "generation_seconds_batch": 22.33032385597471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29621344804763794, "target_z": -0.21679689444415315, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.5315951108932495, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4a5526b47802c798590cd64c30fdec88d3a27889c6367585c6678d9903f4273f.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": "4acc4403acb610152a9a081082be2f2c4e5f4e378fe741784406e5ad7db657a7", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8d950dfc415bf80662cac7d01721cbfd6d86b279801876d350868213391416e", "generation_seconds_batch": 24.2145151339937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.911344289779663, "target_z": 2.03124993777871, "ce": 6.125868320465088, "genuineness": 4.262581825256348, "identity": 0.5911364555358887, "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_Elation/4acc4403acb610152a9a081082be2f2c4e5f4e378fe741784406e5ad7db657a7.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "4b16d99fde41b6680d0629c9c40fba58977aa06a7401a9038a208fee8b0a9e9f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0d95647a42d709195712de57222e55523410f5e354a43bfb1e1d6cd5ca312cf7", "generation_seconds_batch": 25.25397293397691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4454681873321533, "target_z": 1.3828125051851075, "ce": 5.434855937957764, "genuineness": 3.873466968536377, "identity": 0.5340725183486938, "hypothesis": "The 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_Elation/4b16d99fde41b6680d0629c9c40fba58977aa06a7401a9038a208fee8b0a9e9f.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": "4b5e901092f20f92770170470142f3bc4d3b9f56b3f62fdf0a865a7f68365a9e", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I wrote the number on the envelope.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "653f4fb4bd67cc4d668753c8db291b8343c43d4c137268d7af4d17ff6a8ba04b", "generation_seconds_batch": 17.6678274970036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2546273469924927, "target_z": 1.1171874948148925, "ce": 6.332377910614014, "genuineness": 3.7416701316833496, "identity": 0.4056025743484497, "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_Elation/4b5e901092f20f92770170470142f3bc4d3b9f56b3f62fdf0a865a7f68365a9e.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "4c947da2b723232851ef1c2fe4134b6d097204d00e8d66183ff0f4b503c3237c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "062925f68dd778b2bcbfd1aa2431ba0e0dd9169c40dbdd65cc5e74c14d78204d", "generation_seconds_batch": 23.822048300062306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3158588409423828, "target_z": -0.18945312629627686, "ce": 6.332377910614014, "genuineness": 4.331617832183838, "identity": 0.5582716464996338, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4c947da2b723232851ef1c2fe4134b6d097204d00e8d66183ff0f4b503c3237c.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": "4cd8ab72e2882815e5e6fff8190a8ccaee9704085e7b43c95308627f76f3144e", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "577373703e4acb526282e40a7d5e8e05b86f9e3b09bf8725672f46b8d58f006c", "generation_seconds_batch": 16.829588945955038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47372350096702576, "target_z": 0.03027343685186156, "ce": 6.419747352600098, "genuineness": 4.519899368286133, "identity": 0.5596052408218384, "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_Elation/4cd8ab72e2882815e5e6fff8190a8ccaee9704085e7b43c95308627f76f3144e.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": "4cdab2ba2a8ca0d731604f846de15b661089a5702796af85b43898bf87e6515c", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Escribí el número en el sobre.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12f663da687e39ca0551082b9c3cd74f3015d15be3b9b8491b4f2fdb883b0070", "generation_seconds_batch": 15.742755199084058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7382345199584961, "target_z": 0.39843751555532253, "ce": 6.252951145172119, "genuineness": 4.218649387359619, "identity": 0.5740050077438354, "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_Elation/4cdab2ba2a8ca0d731604f846de15b661089a5702796af85b43898bf87e6515c.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "4d0559657b545a29406c0a34a1a3a69e88b22baa69a6d63c1566a54c1e9f1dd0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "266b162813ef46b0127706e47827eddb51c79acc41262236660459e991136589", "generation_seconds_batch": 23.080368431052193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9150429368019104, "target_z": 0.6445312629627687, "ce": 5.796247482299805, "genuineness": 3.6224255561828613, "identity": 0.4829849898815155, "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_Elation/4d0559657b545a29406c0a34a1a3a69e88b22baa69a6d63c1566a54c1e9f1dd0.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "4d7f46115270e134d139ae73d8bfc7170c0a67c69623cc0e12b03b3f305388ea", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fbf85795bdcdcd6b4b7e14e17c144a2c62ef2202056383cd9ac54ba06ba9e5c7", "generation_seconds_batch": 17.02493359800428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.090959310531616, "target_z": 2.28125010370215, "ce": 5.474569320678711, "genuineness": 3.6412534713745117, "identity": 0.3238508403301239, "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_Elation/4d7f46115270e134d139ae73d8bfc7170c0a67c69623cc0e12b03b3f305388ea.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "4d9440a8dd775e9e1ea6975bd927e9ca4b5eee79289591c265facce26d9e179f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3dcbda0fe390a49709933315425890326c231efe6c53afdecea4586810d57f41", "generation_seconds_batch": 21.71621260093525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3751457929611206, "target_z": -0.1069335921296539, "ce": 6.070269584655762, "genuineness": 4.482243061065674, "identity": 0.5220440030097961, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4d9440a8dd775e9e1ea6975bd927e9ca4b5eee79289591c265facce26d9e179f.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "4da9d66aa383752ed073a61b5ee8c3dab68ec3ddf8200e61119597b3e75781c2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2c1e243fc360217d4102e2dc4d3f00f9216c950c2efbe71e987ef474f5be447d", "generation_seconds_batch": 21.87656118592713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2930259704589844, "target_z": 2.56249995851914, "ce": 5.879645347595215, "genuineness": 4.13078498840332, "identity": 0.6207147836685181, "hypothesis": "Je trouvais la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4da9d66aa383752ed073a61b5ee8c3dab68ec3ddf8200e61119597b3e75781c2.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "4dbf6702932ece665d8eb30cf7940e1f3109ed1015e0cbf803183a95ac5190e6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1a09be735982a8eb84e1c34b54e62cf61674eec81c27f1f6f796a9298a73b05f", "generation_seconds_batch": 16.463373410049826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.067615270614624, "target_z": 3.640625010370215, "ce": 5.657250881195068, "genuineness": 4.086852550506592, "identity": 0.31064265966415405, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4dbf6702932ece665d8eb30cf7940e1f3109ed1015e0cbf803183a95ac5190e6.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "4ddf120fb06e8c1f7966638f161bc18ec5f3a5a1e6ca736d2bcf7102e8b311a2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9a764b1fc3beaca8f88fc78d3d45beaa40bc13d63b3b87f3f0a6904dd805ec9c", "generation_seconds_batch": 22.992968678940088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6554432511329651, "target_z": 0.2832031055558468, "ce": 6.038498878479004, "genuineness": 4.193545341491699, "identity": 0.5672861337661743, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4ddf120fb06e8c1f7966638f161bc18ec5f3a5a1e6ca736d2bcf7102e8b311a2.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "4f29794d1f4d7f6f56ad7ea049efc4576841b4334467f57c3212df4799b7309b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0b4f0354895126441fe666b0ad36b8f38dbfed67c82dfe8bbc2c67b974a3e82", "generation_seconds_batch": 21.88113545696251, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8383758068084717, "target_z": 1.9296875362957526, "ce": 5.4388275146484375, "genuineness": 3.540836811065674, "identity": 0.541110634803772, "hypothesis": "The 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_Elation/4f29794d1f4d7f6f56ad7ea049efc4576841b4334467f57c3212df4799b7309b.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "4f6abd688f392c105129bec2e9afc1b530a6155fa11361929f8be7e83c27c8f0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6e546dc316a754b941f6c4d36460f86edbadb784198f1c8c4eae421d00ce1453", "generation_seconds_batch": 20.01161761197727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8785586357116699, "target_z": 0.59374997925957, "ce": 6.284721851348877, "genuineness": 4.287685871124268, "identity": 0.5971720814704895, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4f6abd688f392c105129bec2e9afc1b530a6155fa11361929f8be7e83c27c8f0.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "4f9cbcd5b6a28832ccb6c12e9c9734f6cd92aa9cbe10431e3b675e7802df3bce", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b127ff4c8fdd2681eb1aeb6ef0999ebb996491e350159b847cf717a21cbfd808", "generation_seconds_batch": 24.433581848978065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1311421394348145, "target_z": 0.9453125466659675, "ce": 6.308549880981445, "genuineness": 4.055472373962402, "identity": 0.5017825961112976, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4f9cbcd5b6a28832ccb6c12e9c9734f6cd92aa9cbe10431e3b675e7802df3bce.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "4fbda98b96f499046ef4efbbaf1bc7224b86ebeca20ea24340b95566af7763df", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2d14113297ff988b104a163bc1d3e077427dc8ba5baed874132f03c8fa68637a", "generation_seconds_batch": 23.879590797936544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1255290508270264, "target_z": 0.9374998755574198, "ce": 6.165581703186035, "genuineness": 4.149612903594971, "identity": 0.5401782989501953, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/4fbda98b96f499046ef4efbbaf1bc7224b86ebeca20ea24340b95566af7763df.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "5037b1e0661bbfeef72d2945b5dd3d491a0b7c745dba4dd1683c662858616347", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "24052576547f2f1b9958a0e655d10cd46465d4005857969d2422495a1f97a52f", "generation_seconds_batch": 21.81650149205234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4572354257106781, "target_z": 0.007324233981253306, "ce": 6.260893821716309, "genuineness": 4.545003414154053, "identity": 0.5883651971817017, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5037b1e0661bbfeef72d2945b5dd3d491a0b7c745dba4dd1683c662858616347.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "505aa95d315e22f47608f2440ad494d07d5f9e1b76567975cd436e4a068b0f3b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e9e3988d85054e93c436ddad23cbcd2778bcb6f5bd14860fb7a72d017a6cd081", "generation_seconds_batch": 23.96982458990533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.593700647354126, "target_z": 0.19726563148138437, "ce": 6.141753673553467, "genuineness": 3.9927117824554443, "identity": 0.5785083770751953, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/505aa95d315e22f47608f2440ad494d07d5f9e1b76567975cd436e4a068b0f3b.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "505c8d3cbd4e6eee0d849bf61cf0d805e29a95f2383e39963cf0bbe269fa5b2d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b062c1a1ca2f2aabcd95b96500cf852b441446bda6ef6b765b69756263a69789", "generation_seconds_batch": 23.265388414962217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6428140997886658, "target_z": 0.265625010370215, "ce": 5.959072113037109, "genuineness": 3.9048471450805664, "identity": 0.47870320081710815, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/505c8d3cbd4e6eee0d849bf61cf0d805e29a95f2383e39963cf0bbe269fa5b2d.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "50783ad2850d761f8461c90359da00538c4a963b4772a958c3905bbee8400231", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "56ecc04990be6710238736c4896c0cde680fe953cbd2b51aeb96c82b13c7685d", "generation_seconds_batch": 22.514615427004173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.709277629852295, "target_z": 1.7500000829617202, "ce": 6.2767791748046875, "genuineness": 4.469690799713135, "identity": 0.516086220741272, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/50783ad2850d761f8461c90359da00538c4a963b4772a958c3905bbee8400231.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "508a602518026697d33f2b1ec4df20ccbf51646f376719d171bd11dab5e17084", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ec5cdcd0f4f201ca9ef880fabb33820ed2683302fe4f8c3b074eb019137486d5", "generation_seconds_batch": 22.418488586088642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0974643230438232, "target_z": 0.8984375155553225, "ce": 5.720792293548584, "genuineness": 3.8671910762786865, "identity": 0.22751598060131073, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/508a602518026697d33f2b1ec4df20ccbf51646f376719d171bd11dab5e17084.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "50ad26e0c117a2cb60b57989328887d392c65a6422851ca1f9b7767252bbda88", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7c8f8f2cabd2162773cc54b1b7b11f9f5e6580021f2bc8cf419b4ea5af03c18f", "generation_seconds_batch": 24.333033842034638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5175445079803467, "target_z": 2.8749998340765597, "ce": 6.221180438995361, "genuineness": 3.71028995513916, "identity": 0.1105707660317421, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie standen neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/50ad26e0c117a2cb60b57989328887d392c65a6422851ca1f9b7767252bbda88.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "51052da913c980557fe09c492d4223fbad6730d106d30fc8c8555c880b40694c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a7700e2348e57661ce2d228491e3a59224a7e71972756c29e30765eb511ca378", "generation_seconds_batch": 22.97725818201434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.237788438796997, "target_z": 1.09374997925957, "ce": 6.173524379730225, "genuineness": 4.017816066741943, "identity": 0.32311582565307617, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/51052da913c980557fe09c492d4223fbad6730d106d30fc8c8555c880b40694c.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "51a1865398f8b42ca5307517317035a5bddbae90f5c150eb610b4866623c6aac", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "45e921e8276918abd1b45c4d7db9524eff304f4c7da08661ad289c11443729e1", "generation_seconds_batch": 15.495586931006983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3612737655639648, "target_z": 1.265625093331935, "ce": 6.316492557525635, "genuineness": 4.300237655639648, "identity": 0.49184656143188477, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/51a1865398f8b42ca5307517317035a5bddbae90f5c150eb610b4866623c6aac.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": "51ac13ea2f8eb49226ad62c8627550b826aa3ebb80c5a026847397b958bb83e6", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I wrote the number on the envelope.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3b8a9d4149c252ef15bf0bb5cdf3b932b0cd09b95f3ebb56befc225839e8fb1", "generation_seconds_batch": 17.909004685934633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5295023322105408, "target_z": 0.10791013453736231, "ce": 6.332377910614014, "genuineness": 3.8044304847717285, "identity": 0.38427048921585083, "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_Elation/51ac13ea2f8eb49226ad62c8627550b826aa3ebb80c5a026847397b958bb83e6.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": "5241d0234967dae1a6eb981dce224785980e47e68d284b9e99980addef76498b", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fce7e8357f0eb4e45174b925737c9bfc9711e9237b88986ff004d3cafdf07d74", "generation_seconds_batch": 17.62099951202981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7045567035675049, "target_z": 0.35156248444467747, "ce": 6.109982967376709, "genuineness": 4.3881025314331055, "identity": 0.4681360125541687, "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_Elation/5241d0234967dae1a6eb981dce224785980e47e68d284b9e99980addef76498b.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": "524c61e0e61d9803fbe29d78a22ab6b51e38a754f3227f5ecd87fb3089356b8e", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb589c5685bdfbbd736252f06d8e7cf8829d18ea79408df59ec0b932a6550aa9", "generation_seconds_batch": 16.602132058003917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17413145303726196, "target_z": -0.38671875777766124, "ce": 6.499174118041992, "genuineness": 4.256305694580078, "identity": 0.4749448001384735, "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_Elation/524c61e0e61d9803fbe29d78a22ab6b51e38a754f3227f5ecd87fb3089356b8e.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "52505b60afa4454e3d8b91ff899fc9df7352c73059e2f56e00f917b0b408566c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a7ffcc184ef61548c32fdd4441eefabf93ce5c747cedb720f0a55e1928e0ab0", "generation_seconds_batch": 23.38683703902643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209723711013794, "target_z": 1.0546876192574728, "ce": 6.046441555023193, "genuineness": 4.168440818786621, "identity": 0.6271520853042603, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/52505b60afa4454e3d8b91ff899fc9df7352c73059e2f56e00f917b0b408566c.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "52aa9f7e71f1c36f3f8b0f43245a0113dd8878edad58084b2e5e9ae7660b05b4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "40f09198d2b0f574fde26da66d2fc17d2779cc5d269c7a7f67663faabd4db9ca", "generation_seconds_batch": 23.12384905689396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4709170162677765, "target_z": 0.026367184259307806, "ce": 6.197352409362793, "genuineness": 3.9676074981689453, "identity": 0.2919994592666626, "hypothesis": "The 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_Elation/52aa9f7e71f1c36f3f8b0f43245a0113dd8878edad58084b2e5e9ae7660b05b4.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": "52ad137012cee925171571c354a8c464cf2c277b136126fd2ca3e76999b2d1e8", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "725f3f31e5bc1a5f806d77fb1a6f6652bc3107b66860fdd33d8e55c4d4d35ba7", "generation_seconds_batch": 19.130675061023794, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20640601217746735, "target_z": -0.34179687370372314, "ce": 6.268836498260498, "genuineness": 4.356721878051758, "identity": 0.3548394739627838, "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_Elation/52ad137012cee925171571c354a8c464cf2c277b136126fd2ca3e76999b2d1e8.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "52ca172f68c717935034a55b045cf1e7fcc1956f98517bfb937bed4b092e7250", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "23c51b08f228b2130d42aa31cfd70c68922529f46e55d344a23528abf8d7f4f0", "generation_seconds_batch": 17.045304328086786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8308484554290771, "target_z": 0.5273437681478763, "ce": 6.046441555023193, "genuineness": 3.8922953605651855, "identity": 0.5425726771354675, "hypothesis": "The 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_Elation/52ca172f68c717935034a55b045cf1e7fcc1956f98517bfb937bed4b092e7250.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "534a4afaea5e18ac9b2dd8550874a6e011d13eb5160c14b6b1f616a6534a5d5e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "714a6ae32cbbff1dbb4c7b17bbe50f3328fae770da5e5e366b909391cbcc4c09", "generation_seconds_batch": 22.418488586088642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6859335899353027, "target_z": 3.109374989629785, "ce": 5.526196479797363, "genuineness": 3.8546390533447266, "identity": 0.2751201391220093, "hypothesis": "De deur staan nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/534a4afaea5e18ac9b2dd8550874a6e011d13eb5160c14b6b1f616a6534a5d5e.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "53f31b593058776d7f9f56b0aafeabdd323820c84da4d5e4a01fd73fd19c5c85", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "443ced016a07a66bd396991fac26f8570b4abea143b5e440fdb4751d70505595", "generation_seconds_batch": 16.917030345997773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0123777389526367, "target_z": 2.171875031110645, "ce": 6.372091293334961, "genuineness": 3.9927117824554443, "identity": 0.24974346160888672, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/53f31b593058776d7f9f56b0aafeabdd323820c84da4d5e4a01fd73fd19c5c85.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "a06a8b7d27660b9fb4a2fa5f2be998174ba2f75efeb9f0a7846c3ce66d146298", "generation_seconds_batch": 16.163655983982608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22745463252067566, "target_z": -0.3125, "ce": 6.3641486167907715, "genuineness": 3.9927117824554443, "identity": 0.500633716583252, "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_Elation/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "54bbe713ee76001671269e9b9983f2e23f01a91ec5131e7d89b66e0b79127ae3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "eb4de2e88e94c761b879e148702b686c752091b2fca88ea7e85699884899cb05", "generation_seconds_batch": 22.422820423031226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1620134115219116, "target_z": 0.9882812422223387, "ce": 6.268836498260498, "genuineness": 4.394378662109375, "identity": 0.5853191614151001, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/54bbe713ee76001671269e9b9983f2e23f01a91ec5131e7d89b66e0b79127ae3.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": "54e62280650b580be0d27cf34d7be99c4ad830a02e6897b6dda6b22070e88796", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2a617dcc8bbee35d4d6d78851f0b3b3916cd7c5801008e64aa498727d51b140", "generation_seconds_batch": 24.078296349034645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.67508864402771, "target_z": 0.31054687370372314, "ce": 6.1894097328186035, "genuineness": 4.6203155517578125, "identity": 0.7786306142807007, "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_Elation/54e62280650b580be0d27cf34d7be99c4ad830a02e6897b6dda6b22070e88796.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "550c876aeef24cba3d35dc0007ea7a6f5ab1832c956fe13210fab0b70e1d2b3b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cc1be204c33372e091f34e5b5c5be1aac9b060234541fcb456cfd9f4c15eaa18", "generation_seconds_batch": 22.141028495971113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1807665824890137, "target_z": 2.40624985481699, "ce": 5.990842819213867, "genuineness": 4.168440818786621, "identity": 0.6070427298545837, "hypothesis": "J'ai trouvé la 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_Elation/550c876aeef24cba3d35dc0007ea7a6f5ab1832c956fe13210fab0b70e1d2b3b.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "55a981ed4baa14f1813aa0438f0182f3d4f6c0fe8b389467fe3e86fa4632c476", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4954ff37b5d39d5484e1eb0ec00416fc5b0aff4ef09ae5a7d9b1295452a60249", "generation_seconds_batch": 23.967438363004476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8561067581176758, "target_z": 0.5624999585191399, "ce": 6.316492557525635, "genuineness": 4.042920112609863, "identity": 0.4600617289543152, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/55a981ed4baa14f1813aa0438f0182f3d4f6c0fe8b389467fe3e86fa4632c476.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "55ae39bb85d71df479213688cb48f3d7fd6e4fc6b567ce9515610661c4274488", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "468282738bdd9def9426bf377e478fa77140adbf2c396105dbce3335684537cf", "generation_seconds_batch": 23.675358145032078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9337961673736572, "target_z": 2.06249995851914, "ce": 5.804190158843994, "genuineness": 3.8420867919921875, "identity": 0.14954687654972076, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/55ae39bb85d71df479213688cb48f3d7fd6e4fc6b567ce9515610661c4274488.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "55fb0b57345e32ada6a8a9139bda3bac3f2bd630c5506d0c75149f186de25976", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "500e01c83bd301406b6729feb557abf550ef61e1e42f11e3d1d6bbb98fb4fa68", "generation_seconds_batch": 17.837215775973164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42110195755958557, "target_z": -0.04296873703723123, "ce": 5.665193557739258, "genuineness": 3.7793264389038086, "identity": 0.41346275806427, "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_Elation/55fb0b57345e32ada6a8a9139bda3bac3f2bd630c5506d0c75149f186de25976.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "56c9414a44ee3cdd398847a9f0c2177459a80cb48a48529dff56701f045e33b7", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7f7886d177cd855af0cba9adbd4d2f1c49cbe97cecaad581c963c077755dc594", "generation_seconds_batch": 15.647205361980014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07029157876968384, "target_z": -0.53125002074043, "ce": 6.340320587158203, "genuineness": 4.356721878051758, "identity": 0.5221543908119202, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/56c9414a44ee3cdd398847a9f0c2177459a80cb48a48529dff56701f045e33b7.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "56d9396f229d1a48fbed542052e03a38ba7a013833d0f482d2ddd908c5561ea4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "50023f43f4ab2606312fb84682a76cdddd35c18957e8e56424b0da51ffbcbdb9", "generation_seconds_batch": 23.023645670968108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2527129650115967, "target_z": -0.27734376814787626, "ce": 6.149696350097656, "genuineness": 4.15588903427124, "identity": 0.687690019607544, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/56d9396f229d1a48fbed542052e03a38ba7a013833d0f482d2ddd908c5561ea4.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": "57d31437367a64d7da2d89b6b6ef863cf6b69155e346b675c76c424c886a487e", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f352a0db3519104b2b549a25a7657bb7f61b162b464bc0ec7503b703da297ce", "generation_seconds_batch": 16.364956358913332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7915576696395874, "target_z": 0.47265623185212374, "ce": 6.292664527893066, "genuineness": 4.3504462242126465, "identity": 0.496551513671875, "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_Elation/57d31437367a64d7da2d89b6b6ef863cf6b69155e346b675c76c424c886a487e.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "58083346c363457db85824b64e193487484fffd0fb768f1b83bacee7c71d2868", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f74f7eadf5732ddb78bcf1ea5cbad2b1d12b5ce632074a3bbcfbafb069501252", "generation_seconds_batch": 24.14670889498666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7990849018096924, "target_z": 1.8749998340765597, "ce": 5.637393951416016, "genuineness": 3.860914945602417, "identity": 0.4984889626502991, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/58083346c363457db85824b64e193487484fffd0fb768f1b83bacee7c71d2868.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "5878a88cdf57c02d0f3803143a094bf033b2b438b168b6cca32e9d02744f136d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "132a2776bae6ebb31ec189ce17bc6e7a0fb9e6da895b27200777f9adda3451a4", "generation_seconds_batch": 18.025433639995754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48740512132644653, "target_z": 0.049316428610776133, "ce": 6.0146708488464355, "genuineness": 3.7542223930358887, "identity": 0.44191256165504456, "hypothesis": "The 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_Elation/5878a88cdf57c02d0f3803143a094bf033b2b438b168b6cca32e9d02744f136d.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "587bbc6bbff675c73f54e6ff616446bb05efd13abce8a0c97e2bac4fd486ffe8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "be259c9ad92c43c282c2696f671f60a3c8adbf882344838f4938f8a84f387d29", "generation_seconds_batch": 21.933779336046427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27656808495521545, "target_z": -0.24414062111116938, "ce": 6.213237762451172, "genuineness": 4.306513786315918, "identity": 0.6769104599952698, "hypothesis": "Ik 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_Elation/587bbc6bbff675c73f54e6ff616446bb05efd13abce8a0c97e2bac4fd486ffe8.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "593e8f7eaa6c1810196f32e3480bbde05d9ab77daf0be8c2b76230fb3154bbf5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0e1192cf8fd96270aaa9db593635a1b481a1f5f7e54858138cf985e94c71592a", "generation_seconds_batch": 22.74488310702145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7817350029945374, "target_z": 0.45898438925904567, "ce": 5.990842819213867, "genuineness": 3.8420867919921875, "identity": 0.48055413365364075, "hypothesis": "The 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_Elation/593e8f7eaa6c1810196f32e3480bbde05d9ab77daf0be8c2b76230fb3154bbf5.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "59a812c86df85cac23b71ba61afe12ca16d58d6887a011d2fe051206021d08cc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8ca9be41bb71a25167357df80617edfa313300b88d58d77b2ea106a53f23fa7b", "generation_seconds_batch": 22.054989090072922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.568953514099121, "target_z": 1.5546876192574728, "ce": 4.703137397766113, "genuineness": 3.4843525886535645, "identity": 0.020187530666589737, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd! Zeg maar wanneer je klaar bent!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/59a812c86df85cac23b71ba61afe12ca16d58d6887a011d2fe051206021d08cc.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "59cf7b75f7e05cae5052c65513a105a5a70162813593ae9f44720cf2819f5304", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c64548976f29d2819ce705cf583284281c76b26dfe6de610bc0da96f3d204bb7", "generation_seconds_batch": 16.057577850995585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6980516910552979, "target_z": 1.734375072591505, "ce": 6.09409761428833, "genuineness": 4.193545341491699, "identity": 0.6397751569747925, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/59cf7b75f7e05cae5052c65513a105a5a70162813593ae9f44720cf2819f5304.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "59f41b644f47e5ff6f22dbf05c77ba93d091958ba39864e025175348831f73df", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9be9199ea252fed5c954f57d3f1e8ee7c433865b86d5a5b02ff9638f375a2404", "generation_seconds_batch": 22.81350063800346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6522557735443115, "target_z": 3.06249995851914, "ce": 5.974957466125488, "genuineness": 3.5188708305358887, "identity": 0.5941042304039001, "hypothesis": "Ik 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_Elation/59f41b644f47e5ff6f22dbf05c77ba93d091958ba39864e025175348831f73df.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "5a721e9b86eca04f7c19abb63e2bd4701bfb6ef63241cbae884332d5e69bd303", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2afbfeeec805bda16322b1292504426adc0395701db9e3e6125608b747396101", "generation_seconds_batch": 23.314960247953422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06748512387275696, "target_z": -0.5351562318521237, "ce": 6.213237762451172, "genuineness": 4.061748504638672, "identity": 0.3927919566631317, "hypothesis": "The 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_Elation/5a721e9b86eca04f7c19abb63e2bd4701bfb6ef63241cbae884332d5e69bd303.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "5ac48b58773092b8383a3f24936c9939948998e729d03eeb77dce1e74497aa7e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "06e480a80563dfb7d56318013af04e81060aa28363f1f8676568df1008f6fe18", "generation_seconds_batch": 23.270001942990348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5200304985046387, "target_z": 0.09472660462899851, "ce": 6.086154937744141, "genuineness": 4.118232727050781, "identity": 0.2455594837665558, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5ac48b58773092b8383a3f24936c9939948998e729d03eeb77dce1e74497aa7e.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "5b0b73b61feb1459e8567b72bce355436bf89767e73f338ee99221a6c33054be", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cb8a5bd7f4c482c84982cab9bbfe7ea7caf0ce512b91d2999dcc0390deae7861", "generation_seconds_batch": 16.019124439102598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9674739837646484, "target_z": 2.109374989629785, "ce": 6.372091293334961, "genuineness": 4.042920112609863, "identity": 0.34291791915893555, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem Alten-Fenster. Wir können gemeinsam hineinschaffen!", "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_Elation/5b0b73b61feb1459e8567b72bce355436bf89767e73f338ee99221a6c33054be.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "5b30546a33ec236a753f4d501f4fc163474f57024d5798c07d00d7321432910a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e934be9a387c811fec38968309090254cdf227cf323016da514b9613519a68c", "generation_seconds_batch": 16.305474900989793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8094186782836914, "target_z": 3.28124977185527, "ce": 6.022613525390625, "genuineness": 4.005263805389404, "identity": 0.40665507316589355, "hypothesis": "J'ai trouvé la petite boîte! Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what it contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5b30546a33ec236a753f4d501f4fc163474f57024d5798c07d00d7321432910a.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "5b70a0f23dd5e4ae42a1824f6fdaf68a53cf55a147aa1ad4033a58baffc7e230", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a8e91d0b6b0cfcc96f504777d8cdcb1ad2f7b534f40683d74c40ad1049bd1cca", "generation_seconds_batch": 23.901740805013105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3612737655639648, "target_z": 1.265625093331935, "ce": 5.760505676269531, "genuineness": 3.9425034523010254, "identity": 0.45234715938568115, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5b70a0f23dd5e4ae42a1824f6fdaf68a53cf55a147aa1ad4033a58baffc7e230.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "5c188e71a6287217eadf07f208d3202784068d6cb9e08fd4d2d3957192d0ec09", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "497273c85354f6000f580f7b72d1cc3a1c7d77dba6c7ffc0ad68d9c783b70191", "generation_seconds_batch": 22.982680657994933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4505700170993805, "target_z": -0.001953126296276877, "ce": 5.974957466125488, "genuineness": 4.055472373962402, "identity": 0.7576134204864502, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5c188e71a6287217eadf07f208d3202784068d6cb9e08fd4d2d3957192d0ec09.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "5c4870279f96d01bcde6a2886a00c7a2ae00235f2430dbfe7c8559fb8d40fa14", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b1602d47f8ebe94a8cdf4d2260f6781c276bfaa5ebf255031e17c404a31c6696", "generation_seconds_batch": 24.512202923069708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.145174503326416, "target_z": 0.9648437266670162, "ce": 6.292664527893066, "genuineness": 4.1998209953308105, "identity": 0.19203129410743713, "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_Elation/5c4870279f96d01bcde6a2886a00c7a2ae00235f2430dbfe7c8559fb8d40fa14.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "5c65e8a70a5db8b3be7530f2f2b51703e771260c1165a77f380eb9fb8b6e5715", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "29c2b00b43ce0db9a4dd6509b27689a4bbb43534abcc1e8b09db32bf2824d2ab", "generation_seconds_batch": 16.550164362066425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19938981533050537, "target_z": -0.35156248444467747, "ce": 6.340320587158203, "genuineness": 4.381826400756836, "identity": 0.47741279006004333, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5c65e8a70a5db8b3be7530f2f2b51703e771260c1165a77f380eb9fb8b6e5715.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "5cecedd282454ba8522b99f84d1138d0137ed272806a1baeb4e6d2dd449516b6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a9dd19d11c89e33fbb2a962c643c482a445a0ac16c190c420882ca29e74674a4", "generation_seconds_batch": 23.98640152195003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014161944389343262, "target_z": -0.609374989629785, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.7838809490203857, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5cecedd282454ba8522b99f84d1138d0137ed272806a1baeb4e6d2dd449516b6.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": "5cede2c94f6f0736dd83185569d0e3ab90238a118cb24b20b303ccfd51de8d46", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2ade7d601688e2e2b9f54204726bd1cd6674f358f4e4639aa3ff2f890ea5a23a", "generation_seconds_batch": 22.753808113047853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.971172571182251, "target_z": 0.7226562318521237, "ce": 6.1894097328186035, "genuineness": 3.9299514293670654, "identity": 0.48468315601348877, "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_Elation/5cede2c94f6f0736dd83185569d0e3ab90238a118cb24b20b303ccfd51de8d46.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "9b960309d44dfdf186f323566a53c0ef09b344b922db06013e1a271231440b3d", "generation_seconds_batch": 17.207649796968326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11940503120422363, "target_z": -0.4628906418515994, "ce": 6.0305562019348145, "genuineness": 4.432034492492676, "identity": 0.7286670207977295, "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_Elation/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "5e46a14710ed255521dbf0821b5b4304fbd2f98f420ed1e5495b30a6b1829833", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "120c66fd92e4ea7a4e0b01db407e5038063437b9c8939fa6c8c851924cc20bf9", "generation_seconds_batch": 24.284459954942577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3355042338371277, "target_z": -0.1621093581484006, "ce": 6.006728172302246, "genuineness": 4.13078498840332, "identity": 0.6253867149353027, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5e46a14710ed255521dbf0821b5b4304fbd2f98f420ed1e5495b30a6b1829833.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": "5e8e2b5f25afc456cfca346067c5ca7398142773900cad7abf7f7b21b40079c6", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The road turns left behind the bridge.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdcefbcea978b2aebdeb82ca07d471bbd965510d9a34e22675745542a39e0e29", "generation_seconds_batch": 22.56849841400981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2499064952135086, "target_z": -0.28125, "ce": 6.348263263702393, "genuineness": 4.011539936065674, "identity": 0.46923303604125977, "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_Elation/5e8e2b5f25afc456cfca346067c5ca7398142773900cad7abf7f7b21b40079c6.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "5e90dd6c467cfcc6ab6057237de4dcd12a0ea5cb0130e3a151631905e15d2826", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "63db2c4c3d92c54dd6de49ac5d65e47e9f52ab77edd80a0af668e704d08bf7a1", "generation_seconds_batch": 16.48248175298795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.709277629852295, "target_z": 1.7500000829617202, "ce": 5.696964263916016, "genuineness": 3.9927117824554443, "identity": 0.3766334354877472, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5e90dd6c467cfcc6ab6057237de4dcd12a0ea5cb0130e3a151631905e15d2826.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": "5e9aca12713a1000bdfbafc297aaa3e7192b85555764815a3804a128f2c333b4", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f900b53e531c7ca4aa0cbb6540ccb9482e93c209d4d2efa86e01f0b7fb838a4", "generation_seconds_batch": 23.443660684977658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7761220335960388, "target_z": 0.45117188407393816, "ce": 6.284721851348877, "genuineness": 4.149612903594971, "identity": 0.578526496887207, "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_Elation/5e9aca12713a1000bdfbafc297aaa3e7192b85555764815a3804a128f2c333b4.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "5f03ba3e828a0a20f9eb6fda4782ee3bf2bd63425cf25c4b4323eefca6c9bcbe", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "045979ca7ce7c5c3033db227dfbdd661169d62092d918463382d0a60c0bf3d60", "generation_seconds_batch": 23.57547669392079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9665818214416504, "target_z": 3.49999991703828, "ce": 6.133810997009277, "genuineness": 3.9801597595214844, "identity": 0.5998660326004028, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5f03ba3e828a0a20f9eb6fda4782ee3bf2bd63425cf25c4b4323eefca6c9bcbe.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "5f7f5767e3ca4f9c292750ef1411a0a09c799e2e27a9c092a314e845f2fbacac", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f7ad8a5c439d826df2c7a2a0ca5671c90c08aeef14e3617a42ded648518f81df", "generation_seconds_batch": 17.62369119899813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16992172598838806, "target_z": -0.3925781366664919, "ce": 6.316492557525635, "genuineness": 4.2751336097717285, "identity": 0.6911771297454834, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/5f7f5767e3ca4f9c292750ef1411a0a09c799e2e27a9c092a314e845f2fbacac.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": "5fd21466bd325c85ac1358e70b5f04e0c08ded61285f53aa032ab2f6e9af19f4", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The road turns left behind the bridge.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a3d92fa193fc0d81cb4aae07285691b42292fa7f1f0eaefeefa332e0c8f7811", "generation_seconds_batch": 21.48520233493764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10817912220954895, "target_z": -0.47851561074095433, "ce": 6.4515180587768555, "genuineness": 3.911123275756836, "identity": 0.39063355326652527, "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_Elation/5fd21466bd325c85ac1358e70b5f04e0c08ded61285f53aa032ab2f6e9af19f4.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": "601f9b1a8ee08aa788815fe4dd78168bdfba4d9cc97d6e73b6ec04a40f91d706", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "070c947ca2a804ef2b1a34c6d523286c97afcb4f02edbd10efb8383628ca539c", "generation_seconds_batch": 16.968050522962585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41198086738586426, "target_z": -0.05566407870346096, "ce": 6.3641486167907715, "genuineness": 4.331617832183838, "identity": 0.6180301904678345, "hypothesis": "Las llaves están en la mesa de la cocina. Mire en el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/601f9b1a8ee08aa788815fe4dd78168bdfba4d9cc97d6e73b6ec04a40f91d706.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "608fb85b37dee66e463292d20ee2d8f12548a395fc7438a67e2ac940d5f4a145", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2e65d7afbc8bccd000c2bc106b311efcadcfa97aa04a78b22a550abf978a96b", "generation_seconds_batch": 23.916111625963822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8701392412185669, "target_z": 0.5820313044436288, "ce": 6.268836498260498, "genuineness": 3.672633647918701, "identity": 0.37121787667274475, "hypothesis": "The 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_Elation/608fb85b37dee66e463292d20ee2d8f12548a395fc7438a67e2ac940d5f4a145.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "60912c89f841bc06c49fec810a365193725e98f8d6c3dfc5f9a0a829af36e809", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "42e34bbfc64f7158ed7431bec78d93ca76e67b1ca1a0ff216f5a57ba57903638", "generation_seconds_batch": 21.78701174107846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1583147048950195, "target_z": 2.3749998340765597, "ce": 6.229123115539551, "genuineness": 3.936227321624756, "identity": 0.5307223200798035, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/60912c89f841bc06c49fec810a365193725e98f8d6c3dfc5f9a0a829af36e809.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "614de9347e71e299b328c63f50cabb4f8a6f150e67f16257ef9d3f1c79b84bce", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2cb6af607d533bc74b15fd8edcce4bda349ea634de17ec82aa9e346f880eb2d3", "generation_seconds_batch": 24.316638897988014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25972920656204224, "target_z": -0.2675780951856318, "ce": 6.046441555023193, "genuineness": 3.773050308227539, "identity": 0.3469875454902649, "hypothesis": "The 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_Elation/614de9347e71e299b328c63f50cabb4f8a6f150e67f16257ef9d3f1c79b84bce.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "6152aaed9e0922fffaa1d5ef262e9d9b57b56324f5435c9f5003109ddf33c47a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e6e1ff98f8f0d14e21f9fa2200123ef0b6b17aaf9617828a7ad0ef7f6845532a", "generation_seconds_batch": 17.0054526879685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9515272378921509, "target_z": 0.6953125466659675, "ce": 6.38003396987915, "genuineness": 4.369274139404297, "identity": 0.5561262369155884, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6152aaed9e0922fffaa1d5ef262e9d9b57b56324f5435c9f5003109ddf33c47a.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": "616d88596d12ff040eebc21606386e58f428931f1814911a65ddb3379c564193", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c71702a0504198c7fbf35b16308cebe4ad0c8312770f83ca9ff6469cc3e1f2f", "generation_seconds_batch": 23.95560122304596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8533003330230713, "target_z": 0.5585937888883064, "ce": 6.229123115539551, "genuineness": 4.306513786315918, "identity": 0.6517981886863708, "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_Elation/616d88596d12ff040eebc21606386e58f428931f1814911a65ddb3379c564193.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": "618ea7d9928b1ccd6dcd4a1022010a197001a5c9a082165e26e46aa7c4fd149e", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c1652e0e29b421fe987cec81fbd79719de210e57a3668a3903558c903b285c7", "generation_seconds_batch": 23.15479520696681, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5857923030853271, "target_z": 1.578124968889355, "ce": 6.054384231567383, "genuineness": 3.8295347690582275, "identity": 0.5098087787628174, "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_Elation/618ea7d9928b1ccd6dcd4a1022010a197001a5c9a082165e26e46aa7c4fd149e.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "6241be3684042ffa99afaba9558519e857ead11c70b7ec72bb94ac928deec2d4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b6f8c1b0a5394941bf32ffe29a901822b3d6f85cc5ecfab3d773ac2ee6c1da9e", "generation_seconds_batch": 22.163064071093686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3719885051250458, "target_z": -0.11132811592606186, "ce": 6.133810997009277, "genuineness": 4.394378662109375, "identity": 0.48476696014404297, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6241be3684042ffa99afaba9558519e857ead11c70b7ec72bb94ac928deec2d4.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": "626301f1f9bc27fd01127a5fab1f893cc671a22c91777539acf455459b09b1f8", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e72e744db6cf6ee35edf077a20b6494e5f0f574a5e1aca79c9ebacc488d9774e", "generation_seconds_batch": 16.590294479974546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3979484736919403, "target_z": -0.07519530018536967, "ce": 5.863759994506836, "genuineness": 4.149612903594971, "identity": 0.4040280878543854, "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_Elation/626301f1f9bc27fd01127a5fab1f893cc671a22c91777539acf455459b09b1f8.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": "628497fff0bd676f5642c1db221993281a335debae96cc8fe3019ef8c2fd666b", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The keys are on the kitchen table.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a39ea66ebcc8224b2dc794ac0d881cef201209677846adb52c07fd31e3f79633", "generation_seconds_batch": 23.48382224596571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.888892412185669, "target_z": 1.9999999170382798, "ce": 6.268836498260498, "genuineness": 3.8420867919921875, "identity": 0.6435186862945557, "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_Elation/628497fff0bd676f5642c1db221993281a335debae96cc8fe3019ef8c2fd666b.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": "628819599a0dd8401be2b0e0698eb8424abe83444617871ff6705be0df7ebc9a", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The keys are on the kitchen table.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dac02ad5fda3eb0dd444a7f3f90e074961cc03cbea92517ac3c0867604f65c39", "generation_seconds_batch": 17.926913241972215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4566941261291504, "target_z": 1.3984375155553226, "ce": 6.173524379730225, "genuineness": 3.948779582977295, "identity": 0.47584640979766846, "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_Elation/628819599a0dd8401be2b0e0698eb8424abe83444617871ff6705be0df7ebc9a.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "62e646c835822bd6a584c454746593a7a8472c34b149716651b28a77b0a0d820", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d90d246ef4b69fd85b4b6fce0ad2258e824275dd306669b9572eac088364cd06", "generation_seconds_batch": 17.576559860957786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6512335538864136, "target_z": 0.27734376814787626, "ce": 6.308549880981445, "genuineness": 4.061748504638672, "identity": 0.6952660083770752, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/62e646c835822bd6a584c454746593a7a8472c34b149716651b28a77b0a0d820.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "62f63f48eb0df3a3cda327bb5a3bf6ca5e4c55aad19a2d2ca607350d0ab7dce1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5a6f5e65e4b5f7db7f68cc22895a4d414b270cbd739581769bd4f728299de589", "generation_seconds_batch": 21.387981179985218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3500478267669678, "target_z": 1.2500000829617202, "ce": 6.09409761428833, "genuineness": 4.262581825256348, "identity": 0.6357179880142212, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/62f63f48eb0df3a3cda327bb5a3bf6ca5e4c55aad19a2d2ca607350d0ab7dce1.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "630660327bd75a73ed6d2dc5085d1899e7d105362de02650304d7bff42dcdcbc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "35ded0094a97dac2e065977369c96e952bb9669836624e2b94c6a7e521a97241", "generation_seconds_batch": 17.831443522009067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.971172571182251, "target_z": 0.7226562318521237, "ce": 6.197352409362793, "genuineness": 3.722842216491699, "identity": 0.6325024962425232, "hypothesis": "Ik 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_Elation/630660327bd75a73ed6d2dc5085d1899e7d105362de02650304d7bff42dcdcbc.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "632bd51d0bbd3863d818ee434bd1017514e235ef42aea6ae18fb8be4ceb3ae6e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00d9efeaaf737fc1eee101ca05ce09a2d6628d02974d13164cfb3785dbb5e17c", "generation_seconds_batch": 16.48248175298795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2490143775939941, "target_z": 1.109374989629785, "ce": 5.847874641418457, "genuineness": 3.9801597595214844, "identity": 0.4478813707828522, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/632bd51d0bbd3863d818ee434bd1017514e235ef42aea6ae18fb8be4ceb3ae6e.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "636122b80fc94a7ced503f42bcb91688deeb04494f9eb548d2462d44fcbe98d6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "566de6f2c9d9098e242581402d2c8670a593d78d2f1c59287ba223baa7de26e6", "generation_seconds_batch": 22.464588536066003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.079733371734619, "target_z": 2.265625093331935, "ce": 6.268836498260498, "genuineness": 3.8671910762786865, "identity": 0.45610034465789795, "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_Elation/636122b80fc94a7ced503f42bcb91688deeb04494f9eb548d2462d44fcbe98d6.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "639c8c81be82b059ddf912b020d38223a257a0bb205a531997bc503e420349d2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "27d7da8c3ce8dd6305836ab7053a9333ab79987cdd08d95e58e551bb41f900ff", "generation_seconds_batch": 25.056692978017963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.888000249862671, "target_z": 3.3906248444467746, "ce": 5.4944257736206055, "genuineness": 3.5722172260284424, "identity": 0.23656728863716125, "hypothesis": "The door is still open! I put your coat on the when you are ready!", "wer": 0.16666666666666666, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/639c8c81be82b059ddf912b020d38223a257a0bb205a531997bc503e420349d2.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "63aa2c97d7511bf588b697d89941ddf133254530d6d9cde8a805cfb148c04af4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5349886eb78cbb0d018c6cd84f6870c4b3182b62afac5011bc30dd4c8269c113", "generation_seconds_batch": 21.856287656002678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1255290508270264, "target_z": 0.9374998755574198, "ce": 6.1020402908325195, "genuineness": 4.256305694580078, "identity": 0.5957438349723816, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/63aa2c97d7511bf588b697d89941ddf133254530d6d9cde8a805cfb148c04af4.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "63b6559d5b88c59b427416859773bba4d01b8ab93eb7e17aa64abd30b2b14dac", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "119da31f9b9b25e2209d99d597df2817ecb42c782bee4807c2189a43e2e90639", "generation_seconds_batch": 22.697545998031273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.539996385574341, "target_z": 2.90624985481699, "ce": 5.8875885009765625, "genuineness": 4.074300289154053, "identity": 0.5847561359405518, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt !", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/63b6559d5b88c59b427416859773bba4d01b8ab93eb7e17aa64abd30b2b14dac.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "645726cb63cfbd9f368cec22c976610771b112b95210b8a1ea6c454e29d5521b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7148bdc62caa3b575e755b660da06d1bf24123f9754138c16947841d69e1a94f", "generation_seconds_batch": 20.966229349025525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1474698781967163, "target_z": -0.42382811592606184, "ce": 6.149696350097656, "genuineness": 3.9801597595214844, "identity": 0.7812060117721558, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/645726cb63cfbd9f368cec22c976610771b112b95210b8a1ea6c454e29d5521b.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "6536ea6badeb5ee93d4ede25a7700de9421c165d4735d6ce79fc5d9383c1a0fb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3049ecd4484d07f94e912c35a326661942fe4aba260f720b93d84424257af879", "generation_seconds_batch": 22.80975674802903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7620896100997925, "target_z": 0.43164062111116935, "ce": 6.475345611572266, "genuineness": 3.9425034523010254, "identity": 0.4102568030357361, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6536ea6badeb5ee93d4ede25a7700de9421c165d4735d6ce79fc5d9383c1a0fb.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": "655af9b8994630e597b578ac1bf912693e43be9ca15ce3c0a81accd63532927c", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "224c34fbe54b73cd97c21b86f8e896ceb4a361dc458d1fcf302d5a73d7099e96", "generation_seconds_batch": 21.47142975591123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9795920252799988, "target_z": 0.734374989629785, "ce": 5.959072113037109, "genuineness": 4.218649387359619, "identity": 0.6872107982635498, "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_Elation/655af9b8994630e597b578ac1bf912693e43be9ca15ce3c0a81accd63532927c.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "6573830d1feccb0e15418dfea542ec435c6ea9ef463be6d95601d7e2356870e6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "694dec5e808b089f63ffe48f9ca8675d606f8bcb07e77d4b54baace94c0f7b21", "generation_seconds_batch": 23.01738126692362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.427737236022949, "target_z": 2.75000008296172, "ce": 6.054384231567383, "genuineness": 3.8044304847717285, "identity": 0.31827664375305176, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6573830d1feccb0e15418dfea542ec435c6ea9ef463be6d95601d7e2356870e6.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "671b5054584625e3f704810e173742f1698839512b56764554a1176d8da5c43b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8ee8942d151bbd741f02d965d29c33bf9b8571c08a1c2be9550cb937aad35c8a", "generation_seconds_batch": 22.085373939946294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19377684593200684, "target_z": -0.359374989629785, "ce": 6.268836498260498, "genuineness": 4.3504462242126465, "identity": 0.7266420125961304, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/671b5054584625e3f704810e173742f1698839512b56764554a1176d8da5c43b.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "67213c772fcdaef3c173f3341d4b8ba655c7f8b524c99524707ab60efe4ef08c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d0b3cfa1c1364e5d580486e8d8e71dfed1812089c3c9ee1aab1b153d35cb3005", "generation_seconds_batch": 21.93996504403185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1507874727249146, "target_z": 0.9726562318521237, "ce": 6.09409761428833, "genuineness": 3.898571252822876, "identity": 0.5140396952629089, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/67213c772fcdaef3c173f3341d4b8ba655c7f8b524c99524707ab60efe4ef08c.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "6742d666acf4e05c9ce7c21a3a9caf639b0d4fd0dfaa2c4a81e55a2a3cbb31fc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c624d1b80371882bf6735b64fa17ee67432558f87f9cfe5ecac453f5bcacca2a", "generation_seconds_batch": 16.305474900989793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1134111881256104, "target_z": 2.3125001244425802, "ce": 5.855817794799805, "genuineness": 4.2751336097717285, "identity": 0.585732102394104, "hypothesis": "J'ai trouvé la 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_Elation/6742d666acf4e05c9ce7c21a3a9caf639b0d4fd0dfaa2c4a81e55a2a3cbb31fc.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": "67ceb782f49ea599d52bda6f860f829d89bbb510e9ba03a2328f954988454fed", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5ec4f0cacfbe7dc33ef1c27b5da7134fcfd9d5a3e28aae196681b2320bc283c", "generation_seconds_batch": 22.09551269793883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6540400385856628, "target_z": 0.28125002074043004, "ce": 6.332377910614014, "genuineness": 4.231201171875, "identity": 0.582962155342102, "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_Elation/67ceb782f49ea599d52bda6f860f829d89bbb510e9ba03a2328f954988454fed.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "69643ad33c9149a50a46bbdd856f9c826d13b244de98c86b446fb35e59f4da19", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e615cca510bf83e84eb2447224552d959c8b87822c43cde2ecf8b00c092dd5ef", "generation_seconds_batch": 24.58720099402126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9403012990951538, "target_z": 0.6796875362957525, "ce": 6.395919322967529, "genuineness": 4.080576419830322, "identity": 0.5692600011825562, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/69643ad33c9149a50a46bbdd856f9c826d13b244de98c86b446fb35e59f4da19.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "69723cf64b45baaee0fd03fbdd3bded999cb6178889542ec26774b9f418d688d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ab93607f4c3c9c4a63a50de8b12b341cb551ff9b2128a176d3a62e9694ef9673", "generation_seconds_batch": 16.729105298989452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.215336561203003, "target_z": 1.06249995851914, "ce": 6.086154937744141, "genuineness": 4.306513786315918, "identity": 0.5922000408172607, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/69723cf64b45baaee0fd03fbdd3bded999cb6178889542ec26774b9f418d688d.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "69a22c53cb576959266ae4e523b06173ffc5e065bd79058ec33636d899ab1ba7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ab38c4f7c0dfece33ddbde8807e97ae521e1b72102f34385765b4d56327bdef5", "generation_seconds_batch": 22.542284039082006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3051440715789795, "target_z": 1.18750004148086, "ce": 5.855817794799805, "genuineness": 4.193545341491699, "identity": 0.5485602617263794, "hypothesis": "La porte 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_Elation/69a22c53cb576959266ae4e523b06173ffc5e065bd79058ec33636d899ab1ba7.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "69e48957325aa6cb4fd194e16e6ae87de04f61dbdef4403ca2207e6d42a502b9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9f50311f5154369c0a37b51062a6478e78d69b938e4158df061f6d4b1c80c609", "generation_seconds_batch": 23.445243839058094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1283355951309204, "target_z": 0.9414062111116936, "ce": 6.1020402908325195, "genuineness": 3.785602569580078, "identity": 0.5054926872253418, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/69e48957325aa6cb4fd194e16e6ae87de04f61dbdef4403ca2207e6d42a502b9.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "6a46e137c93d380d2487a2242d31f2f13774d3d480d0760c97c5ad2bf8c3ff76", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4a15c6bfd44e8302af5bd413e15d6d59cacfa3d6613fdb6ff7395b98f94f03ad", "generation_seconds_batch": 21.50097350194119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.889784574508667, "target_z": 0.609374989629785, "ce": 6.062326908111572, "genuineness": 3.911123275756836, "identity": 0.4551408886909485, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6a46e137c93d380d2487a2242d31f2f13774d3d480d0760c97c5ad2bf8c3ff76.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "6a52955003eda3f2bd2cf0fbb89521a3fc1977b51943817ad827497e8dab0a6c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f4e588894ffa9fd53c8ca33b385a069d2db09d5209e687e3270dffa2bf12b063", "generation_seconds_batch": 24.433201162028126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.117109775543213, "target_z": 0.925781366664919, "ce": 6.252951145172119, "genuineness": 4.049196243286133, "identity": 0.43983781337738037, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6a52955003eda3f2bd2cf0fbb89521a3fc1977b51943817ad827497e8dab0a6c.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "f9999ecf05cca2e8e690afc0481f619b93ff50f6b97aaae0739ebf72c28577b9", "generation_seconds_batch": 19.52414163609501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06748512387275696, "target_z": -0.5351562318521237, "ce": 6.443574905395508, "genuineness": 4.080576419830322, "identity": 0.3689400553703308, "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_Elation/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.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": "6b50e06df444ee11481cbdbf42e5fd8127d1a85295e3d3773337171faa8eec49", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36e85d5789ed5588cc6664e54120b624b0a84c4cab8585cc324a2ce200a7a3fc", "generation_seconds_batch": 21.318990878062323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8327627182006836, "target_z": 1.9218748651872049, "ce": 6.332377910614014, "genuineness": 4.362998008728027, "identity": 0.5608124732971191, "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_Elation/6b50e06df444ee11481cbdbf42e5fd8127d1a85295e3d3773337171faa8eec49.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "f3195a9329a7b64c22634cbd970938f63f45b13fe4d3d6d3267eb9bb5aba9797", "generation_seconds_batch": 21.021047381917015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10958236455917358, "target_z": -0.47656248444467747, "ce": 6.078212261199951, "genuineness": 4.595211505889893, "identity": 0.8088178634643555, "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_Elation/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "6bf72cbd4221a0e2b275fbad2889613254a04910b317fec1cab29ed38a141b03", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9fd0d5ea8b145e54488b30050b8a70edc0e2a01669454ac7d65d1307f1dc275f", "generation_seconds_batch": 15.82979614904616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.237788438796997, "target_z": 1.09374997925957, "ce": 5.831989288330078, "genuineness": 3.7416701316833496, "identity": 0.46297186613082886, "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_Elation/6bf72cbd4221a0e2b275fbad2889613254a04910b317fec1cab29ed38a141b03.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "6c21716c5da6f80ca9c01fa572c889d6a2a2de979df88ce4c55fd982ef4c25fd", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d030f3623547873c87a388bef9f317d55e7424df9f41b7578937ec7fd565434d", "generation_seconds_batch": 23.670831549097784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6250829696655273, "target_z": 1.6328123392616671, "ce": 5.919358730316162, "genuineness": 4.042920112609863, "identity": 0.221038356423378, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6c21716c5da6f80ca9c01fa572c889d6a2a2de979df88ce4c55fd982ef4c25fd.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": "6c50699da3c6eeca42555538d5e69faac8139b28b16ee03340668bcea91d0461", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "830000e5a402adfd60e0e23993834e243b7ecc13b42ae834f4f9bafd268110bc", "generation_seconds_batch": 21.70226614899002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1367549896240234, "target_z": 0.9531248859276348, "ce": 6.38003396987915, "genuineness": 4.319066047668457, "identity": 0.4825361371040344, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6c50699da3c6eeca42555538d5e69faac8139b28b16ee03340668bcea91d0461.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "6c9942dfb7165ba2144c995096ddb2642024e7c5fce4d7f831735eefaced79e5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ab2432ea9e67158d24f83f54c41ff6e62f5e0899b68b2b960853b4cb102fafc3", "generation_seconds_batch": 17.47067705099471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4838666915893555, "target_z": 2.8281248029659145, "ce": 6.23706579208374, "genuineness": 3.898571252822876, "identity": 0.6699056625366211, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6c9942dfb7165ba2144c995096ddb2642024e7c5fce4d7f831735eefaced79e5.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "6c99968ac28a1b36e3a4ea9087f1cc4c1a5e4121f00ec6fc4bc8e7d69658e93a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5098e6cd07e68d85aeb28922c6bca77f5e3a4b4ab1348a2b1439c20c5803aab2", "generation_seconds_batch": 24.107150188996457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9234623908996582, "target_z": 0.65625002074043, "ce": 6.09409761428833, "genuineness": 3.7667744159698486, "identity": 0.43983083963394165, "hypothesis": "The 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_Elation/6c99968ac28a1b36e3a4ea9087f1cc4c1a5e4121f00ec6fc4bc8e7d69658e93a.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "6cf7b215a88a0df7c9deb832470d5df248efdd17ba70052a983467555ad241e6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0b47b85dce938ba8670453b23f3feac1d0d6dc3a30e65ac57ad589fbd2c7a7b2", "generation_seconds_batch": 16.729105298989452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6428140997886658, "target_z": 0.265625010370215, "ce": 6.149696350097656, "genuineness": 4.482243061065674, "identity": 0.6496247053146362, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6cf7b215a88a0df7c9deb832470d5df248efdd17ba70052a983467555ad241e6.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "6d09fe1d409e82211dfa50c8ae1aede695fa4b48152f9195af1951f51cfb6b4f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "028c5c0c688e775680b975c0d744ec204c2a27f14c20e7c0447e1bf0088fbca1", "generation_seconds_batch": 24.45710303389933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1872718334197998, "target_z": 1.0234375985170427, "ce": 6.459460258483887, "genuineness": 4.193545341491699, "identity": 0.35393092036247253, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6d09fe1d409e82211dfa50c8ae1aede695fa4b48152f9195af1951f51cfb6b4f.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "6d284243c795b60211dce50c80dad326dc095a72170a8b443d49bb40d3f8d237", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bbee287f47b6740480bb92a970bfbe6ae6772a574ea166b31a10ca77516064dd", "generation_seconds_batch": 20.994528125040233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.551222324371338, "target_z": 2.921874865187205, "ce": 5.689021587371826, "genuineness": 4.017816066741943, "identity": 0.5417718887329102, "hypothesis": "J'ai trouvé la petite boîte. It is pretty fenêtre. We've regarded ensemble what it contains.", "wer": 0.631578947368421, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6d284243c795b60211dce50c80dad326dc095a72170a8b443d49bb40d3f8d237.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "6d564087091938c50d3f14c9330845de07c6b5ea2e5259daebfde1febc1fa6a6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5b296f3c8da892ec218135844e9fef19546cb87d25ed92dadc8c33cbc2a50301", "generation_seconds_batch": 21.70181178499479, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0581735372543335, "target_z": 0.84374997925957, "ce": 5.982900142669678, "genuineness": 3.7793264389038086, "identity": 0.6181872487068176, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6d564087091938c50d3f14c9330845de07c6b5ea2e5259daebfde1febc1fa6a6.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "6e0cb71a475bc4f3178b6e7e483730c3c0e18a515950103e01f0ff307fcb1408", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3ebcbe767c51d4191c13442e214a420fc50af32f2f609082b6b1b33309b63d15", "generation_seconds_batch": 18.122190579073504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2372773289680481, "target_z": -0.29882811592606184, "ce": 6.427689552307129, "genuineness": 3.8671910762786865, "identity": 0.2448699176311493, "hypothesis": "The 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_Elation/6e0cb71a475bc4f3178b6e7e483730c3c0e18a515950103e01f0ff307fcb1408.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "6e24a0e3fc75e6291e5e1b86accbb62c06dbe9bfe9c8d12e7915a5d707b68698", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "70192a45e797e934a5bc067621cca15652f4d16e64dffe08d3fef7439774f516", "generation_seconds_batch": 25.014552796958014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.427737236022949, "target_z": 2.75000008296172, "ce": 6.221180438995361, "genuineness": 4.080576419830322, "identity": 0.45074254274368286, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what it contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6e24a0e3fc75e6291e5e1b86accbb62c06dbe9bfe9c8d12e7915a5d707b68698.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "6e4a1513c4d460e07a3d5135f4d89c365690252f4d102009676531b1596abb26", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "61f464713a79545a529a55bbc73d913a10b1877424fca7a1fcb4b67edae590cc", "generation_seconds_batch": 21.48699527909048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23026111721992493, "target_z": -0.3085937474074463, "ce": 6.022613525390625, "genuineness": 4.017816066741943, "identity": 0.6906942129135132, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/6e4a1513c4d460e07a3d5135f4d89c365690252f4d102009676531b1596abb26.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "6f9d1f0a656c00ddc641c83f92e711fd87996ab27f0d461ce69a3e61f7a75238", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "34be470422f5cdcef928c4c924750b8eeb7d5d4e7e6646039af996f23ec509b2", "generation_seconds_batch": 22.75308428599965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6410298347473145, "target_z": 3.046874948148925, "ce": 6.332377910614014, "genuineness": 4.074300289154053, "identity": 0.3766687512397766, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "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_Elation/6f9d1f0a656c00ddc641c83f92e711fd87996ab27f0d461ce69a3e61f7a75238.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": "6fff70f3bbc2031b06342843b66c6692179472a8e8ca371ba87c1cfe0c514ea1", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33bfa74a1a6b6328ced3feeec6c787cf038b7762a81a9a89e0da4e7bcd413890", "generation_seconds_batch": 16.86192427703645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14887312054634094, "target_z": -0.421874989629785, "ce": 6.086154937744141, "genuineness": 4.293961524963379, "identity": 0.609514594078064, "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_Elation/6fff70f3bbc2031b06342843b66c6692179472a8e8ca371ba87c1cfe0c514ea1.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "70018d6c75539f7077f9425f5b84241aacc28d447d6af3fc9f9f1fe60f59ace0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "edcad12d95d1808674977d0bebaa831143176b9b19f99709d85791eb9f0744e1", "generation_seconds_batch": 22.474981648963876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5081028938293457, "target_z": 0.07812496888935495, "ce": 6.41180419921875, "genuineness": 4.124508857727051, "identity": 0.5365819931030273, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/70018d6c75539f7077f9425f5b84241aacc28d447d6af3fc9f9f1fe60f59ace0.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "704ae4226924dd9096694700a664572e68b64df6d0aa92f22f0148f8a5e814fe", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "67f8d97c051d9be7a0e64a95cf4d3c3dde69a3bc2f7844f22a550f29f7d0fc9b", "generation_seconds_batch": 16.39090766396839, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5184366703033447, "target_z": 1.484374906668065, "ce": 5.689021587371826, "genuineness": 3.5973212718963623, "identity": 0.5631879568099976, "hypothesis": "Ik 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_Elation/704ae4226924dd9096694700a664572e68b64df6d0aa92f22f0148f8a5e814fe.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "71a6f7b5d156f4fb3e143ebb0de4a6133496940b27d6572ee9097fdc7e919457", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4febba26071594b6861c18341280a7e59e892f6a159e0838b80668212020cecd", "generation_seconds_batch": 22.86867048998829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3275959491729736, "target_z": 1.2187500622212901, "ce": 6.0305562019348145, "genuineness": 3.9425034523010254, "identity": 0.5060870051383972, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/71a6f7b5d156f4fb3e143ebb0de4a6133496940b27d6572ee9097fdc7e919457.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "71eaa8d4ee97ca572c1ef4aea54c9fb0366244ee718c3ecdcb77a7efd62492e4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "55a8ab8ed4fc68ee84d912aa0c7e4fa6953755ee7d309e0d95713125c5f9a379", "generation_seconds_batch": 24.333033842034638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9553558826446533, "target_z": 3.484374906668065, "ce": 5.974957466125488, "genuineness": 3.6663577556610107, "identity": 0.2739662528038025, "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_Elation/71eaa8d4ee97ca572c1ef4aea54c9fb0366244ee718c3ecdcb77a7efd62492e4.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "72295fac4b936523eef67de1ba63fce871557c6d3d1abe863ff47bdcfc0ad210", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9cdd2fe7535d14be7e1ca8eca23203ca5dd23c4bf3566e435f74bdf5f2893a1c", "generation_seconds_batch": 20.99730434594676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6185779571533203, "target_z": 3.0156249274084947, "ce": 5.839932441711426, "genuineness": 4.005263805389404, "identity": 0.5584966540336609, "hypothesis": "De deur 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_Elation/72295fac4b936523eef67de1ba63fce871557c6d3d1abe863ff47bdcfc0ad210.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "725b3b1946779f8494b0f48c269b61c5bca2fb2095277085c588db8d261a8afb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f369a1a5d8ef1e0897caf328ad6d8fd9aecc2e6e518db538acfc529866e131f3", "generation_seconds_batch": 23.573504457017407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2751648426055908, "target_z": -0.24609374740744624, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.6466789841651917, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/725b3b1946779f8494b0f48c269b61c5bca2fb2095277085c588db8d261a8afb.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "725e46d74cb4f1f5fa541f32a005c6e010ec38972b8de79560defb47994b170d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b374558a36cede001afaa36917717de4d460497be3ad5d81bc012ac9833720c9", "generation_seconds_batch": 22.085373939946294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20780925452709198, "target_z": -0.3398437474074463, "ce": 6.300607204437256, "genuineness": 4.545003414154053, "identity": 0.6521831750869751, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/725e46d74cb4f1f5fa541f32a005c6e010ec38972b8de79560defb47994b170d.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "7319f28aa0c98fd093c4771997de4531b1e80fb5455aee35a1625e688c0144e1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6be2cb31d8a4e019d0618dbea08ac817333ef12d7cee2fb33ed33c8059c77865", "generation_seconds_batch": 21.80526730895508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0244958400726318, "target_z": 0.7968751140723652, "ce": 6.109982967376709, "genuineness": 4.086852550506592, "identity": 0.685354471206665, "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_Elation/7319f28aa0c98fd093c4771997de4531b1e80fb5455aee35a1625e688c0144e1.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "731e15ffa003d4f68db254d7be2715cf1cbb46825ab68d5c2848ce97e9f6d45a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "33f913e9642637a7e73cd74fc0607e374f73ab39a7e057b4c1978a6d07541b78", "generation_seconds_batch": 22.207357897073962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8196225166320801, "target_z": 0.5117187577776613, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.5501010417938232, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/731e15ffa003d4f68db254d7be2715cf1cbb46825ab68d5c2848ce97e9f6d45a.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "737cc6a0f8eb4bb1aad2be48be52401d7e709404fe486d79695371b10ced937f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bae597744aa94be5b72ab2c2134d7b5045ca19e465d55f60a658031e286a5e4b", "generation_seconds_batch": 21.841958752949722, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3145856857299805, "target_z": 3.984374906668065, "ce": 5.589737892150879, "genuineness": 3.9801597595214844, "identity": 0.6082685589790344, "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_Elation/737cc6a0f8eb4bb1aad2be48be52401d7e709404fe486d79695371b10ced937f.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": "741588d9c28bf235e7dfe55c09ea0b7ea49255d6be3203f58cdd70afb0e89df0", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Someone moved the little blue chair.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59f8b9386ceb56fa4ef8b642b90c2e87cf1c75b95955ce89b2d0f36df584db3c", "generation_seconds_batch": 21.52861760603264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6077330708503723, "target_z": 0.21679689444415315, "ce": 6.435632705688477, "genuineness": 4.243753433227539, "identity": 0.49781113862991333, "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_Elation/741588d9c28bf235e7dfe55c09ea0b7ea49255d6be3203f58cdd70afb0e89df0.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": "741699a7e74ebcec27a41ccca36e906305b2b8fb11304f5f74215b77156800c2", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The road turns left behind the bridge.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93e084025275faeb410968b97ee702a064089c240540a23585dc298a6056581b", "generation_seconds_batch": 15.50870164996013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13624393939971924, "target_z": -0.43945312629627686, "ce": 6.332377910614014, "genuineness": 3.973883628845215, "identity": 0.2923159599304199, "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_Elation/741699a7e74ebcec27a41ccca36e906305b2b8fb11304f5f74215b77156800c2.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "744b0a815004df6b6edaadd9f68b1590993c1d18693a1359d884cc4defc5ad73", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f595ee64b497c15cdc58c3f4b1812c8973e9e327d0611fe1844d067f09ea5d85", "generation_seconds_batch": 20.966229349025525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3600609302520752, "target_z": -0.12792971018484536, "ce": 5.959072113037109, "genuineness": 4.086852550506592, "identity": 0.49901270866394043, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/744b0a815004df6b6edaadd9f68b1590993c1d18693a1359d884cc4defc5ad73.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "74a474289adc0e3d7250f927896a7afa52c346f47ccebf568f17da59267e4964", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4117683f1e53476a01a898139cf3c8002422c725615efa7e501e036288b3d60e", "generation_seconds_batch": 23.04711867601145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3158588409423828, "target_z": -0.18945312629627686, "ce": 6.221180438995361, "genuineness": 3.911123275756836, "identity": 0.4380108714103699, "hypothesis": "The 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_Elation/74a474289adc0e3d7250f927896a7afa52c346f47ccebf568f17da59267e4964.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "74ceaa4ef8feae1e6b3ef439cf26ef558560f708cd0849cf7bc433cc7480f903", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6d820e7d0c420171e2b1bc11120865a35b0fc52d49f61ca1413a4866dcdcb24a", "generation_seconds_batch": 22.12097177701071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8336549401283264, "target_z": 0.53125002074043, "ce": 6.221180438995361, "genuineness": 3.8295347690582275, "identity": 0.3714829683303833, "hypothesis": "The 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_Elation/74ceaa4ef8feae1e6b3ef439cf26ef558560f708cd0849cf7bc433cc7480f903.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "74f21f1edd186b3260e6f399d52fe88f01b989e9f5d04ccbdb2ab38db11c85fa", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "240133faa05c47f1c0346bc3bca1ccf2527af19bb9a036fa4fe4ef504f280c06", "generation_seconds_batch": 21.763898340053856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1919925212860107, "target_z": 2.421874865187205, "ce": 5.323658466339111, "genuineness": 3.5816311836242676, "identity": 0.5491200685501099, "hypothesis": "The 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_Elation/74f21f1edd186b3260e6f399d52fe88f01b989e9f5d04ccbdb2ab38db11c85fa.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "759e48bf23cbbcf4e7b1868c28803daccde235c91e71f7bccec8d0aec3601682", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "68d36267dc04372dfc097a1ccbb46577831e8a7bcfe8bcbc5ed6ee7e3e9f26fb", "generation_seconds_batch": 25.1211202070117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0048503875732422, "target_z": 0.7695312629627687, "ce": 6.229123115539551, "genuineness": 4.413206577301025, "identity": 0.6510125398635864, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/759e48bf23cbbcf4e7b1868c28803daccde235c91e71f7bccec8d0aec3601682.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "75d1137acf4d97eca925657215fe2f368e871f6a7a627012f86e88ee4e4a7f5e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7b087f5a6ff276bfe1b47b5c2c115a631ae83069a940f02b8e7d77cfc6a4860a", "generation_seconds_batch": 22.234008386032656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4004041254520416, "target_z": -0.07177736027753018, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.4081652760505676, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/75d1137acf4d97eca925657215fe2f368e871f6a7a627012f86e88ee4e4a7f5e.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "75fa04b651bd4781d506bf4cb8c53b2a8263f75ff551764f8fff2358ae7afd4a", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "434a90170ca65e8f43ab43733821c1b65fdec65de4996770990a5402dc15ef78", "generation_seconds_batch": 17.49216257291846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5038931965827942, "target_z": 0.07226563148138439, "ce": 5.95112943649292, "genuineness": 4.005263805389404, "identity": 0.6465374827384949, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/75fa04b651bd4781d506bf4cb8c53b2a8263f75ff551764f8fff2358ae7afd4a.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": "764a57741f92d51d6d197e1d14817fcaa27482e894a1c735d3c738b45a33abe9", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I wrote the number on the envelope.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76e60107ada72c36fcb5846f5d24ba686aa0f03583e9f33e7cb7e3990abfe163", "generation_seconds_batch": 17.909004685934633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32989126443862915, "target_z": -0.16992186333350812, "ce": 6.324435234069824, "genuineness": 3.9173994064331055, "identity": 0.4678054749965668, "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_Elation/764a57741f92d51d6d197e1d14817fcaa27482e894a1c735d3c738b45a33abe9.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": "76d25bb7b4925450377f77df2f3d2176fb6b522f10378096976132d2b1027d56", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f061cd1aae96ea43f2c9fa3c492493fb026c14c58a16b58b578e6d47f1e5eb44", "generation_seconds_batch": 15.128525372943841, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1134111881256104, "target_z": 2.3125001244425802, "ce": 6.38797664642334, "genuineness": 4.168440818786621, "identity": 0.18137773871421814, "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_Elation/76d25bb7b4925450377f77df2f3d2176fb6b522f10378096976132d2b1027d56.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "776fbd6d572a715c7da145901a0ee3b69cb5e5e93e4a8ff0932bff53a40b68ee", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fcfbe96e6c7f45a98ec032042f54934f9f24f393f708b2c2abcddb50dce4b92c", "generation_seconds_batch": 22.649113182909787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3846176862716675, "target_z": -0.09374997925956996, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.6402839422225952, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/776fbd6d572a715c7da145901a0ee3b69cb5e5e93e4a8ff0932bff53a40b68ee.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "847760e1cb28358a9130b3da8ce715b8d4480ea0611a979148e1c668c8a68800", "generation_seconds_batch": 17.780143831972964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10116291046142578, "target_z": -0.48828124222233876, "ce": 6.1020402908325195, "genuineness": 4.808597087860107, "identity": 0.7733295559883118, "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_Elation/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.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": "77a7e556553d72519e2d96e3430d75dadca9cdb0b737f7ba718215244216b52f", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2f22d028cf13dd5e354ae0d409914d0666181ef2fafbc64291c640a6e5b19413", "generation_seconds_batch": 16.829588945955038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16150227189064026, "target_z": -0.4042968944441532, "ce": 6.41180419921875, "genuineness": 4.362998008728027, "identity": 0.7241870164871216, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/77a7e556553d72519e2d96e3430d75dadca9cdb0b737f7ba718215244216b52f.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "77d36cbc5548fdc53e91beda0f3366cb317dc5f58b4a30221d180ea25d288980", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "68729708d95c51af92751a2810c8c88f364966a5ee0f4d27bcd424fb7cbf41a6", "generation_seconds_batch": 23.663636183948256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5296626091003418, "target_z": 1.4999999170382798, "ce": 6.117925643920898, "genuineness": 4.394378662109375, "identity": 0.6024656295776367, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/77d36cbc5548fdc53e91beda0f3366cb317dc5f58b4a30221d180ea25d288980.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "786092b1baf35c58ee0a5cbf7679f1d32df03e9611e391f3401fbafccd128c02", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "846c4109b650809919a41d3bb89aad4f27c1c80b4e196b8275c9b1323547f0a2", "generation_seconds_batch": 23.822048300062306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30463290214538574, "target_z": -0.20507813666649188, "ce": 6.324435234069824, "genuineness": 4.519899368286133, "identity": 0.22541378438472748, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/786092b1baf35c58ee0a5cbf7679f1d32df03e9611e391f3401fbafccd128c02.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "7866295b8928c195abd211e8bc417f7c80896ea3122fc8127915aaaf6f37e8c6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "70d066061c780ec116f616e42b6aa0aff15e93229ea3558c4ac583b858bca358", "generation_seconds_batch": 23.557680501951836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.767702579498291, "target_z": 0.43945312629627686, "ce": 6.173524379730225, "genuineness": 4.042920112609863, "identity": 0.48155754804611206, "hypothesis": "The 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_Elation/7866295b8928c195abd211e8bc417f7c80896ea3122fc8127915aaaf6f37e8c6.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "787fae3ea9cebdf71c5a8e7aa309abd62287eb0e80cde97b9dcef8b9bf9400ad", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dc5fe0482dc1bf51e9b3f2a05690bfbc6664697e7ff51a85256cad9d2af3a5c1", "generation_seconds_batch": 16.40843816800043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3719885051250458, "target_z": -0.11132811592606186, "ce": 6.316492557525635, "genuineness": 4.375550270080566, "identity": 0.4566725790500641, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/787fae3ea9cebdf71c5a8e7aa309abd62287eb0e80cde97b9dcef8b9bf9400ad.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "78ba91fbacba40e89ab4d864e0c97d1f6b081baa4b52fa43db921057cbce1752", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a48469fde8029acc0196cc96b0c7db943d7b8c912b4962d2e1f1a060b31adbe0", "generation_seconds_batch": 24.42343245598022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3042519092559814, "target_z": 2.578124968889355, "ce": 6.09409761428833, "genuineness": 4.080576419830322, "identity": 0.4083723723888397, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/78ba91fbacba40e89ab4d864e0c97d1f6b081baa4b52fa43db921057cbce1752.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "78edb20757b78c711c595c8fd2cdf99f5fac76f3f472d209a00229bdf20dfcd9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "265205169bb5686a6b18e223be65a7b12300848e5ce6ec45ae9483b8146aee1f", "generation_seconds_batch": 23.42483916610945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1760458946228027, "target_z": 1.0078125881468276, "ce": 6.316492557525635, "genuineness": 3.8671910762786865, "identity": 0.39946693181991577, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/78edb20757b78c711c595c8fd2cdf99f5fac76f3f472d209a00229bdf20dfcd9.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "78f5957c30bde4ee1b3a895035ee9a417f374921a974b76eff6335cf6584acbd", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4e3c75b7dbed82c74e3be6440b4e2cd896fcb8af2e6791192b58ec225f39104e", "generation_seconds_batch": 23.38683703902643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.562448263168335, "target_z": 2.9374998755574198, "ce": 5.967014789581299, "genuineness": 3.9299514293670654, "identity": 0.49497103691101074, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/78f5957c30bde4ee1b3a895035ee9a417f374921a974b76eff6335cf6584acbd.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "793869eb0b0f95e7cb933186e1a5a1ff037d25c597db264a7c1c8d01d5b33d8c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ef8e7b3cf7cddc1064746b59d941b2d2c80befe43ed9b977a9b839ce5d68a062", "generation_seconds_batch": 20.4036695510149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3668866157531738, "target_z": 1.2734374325936024, "ce": 5.959072113037109, "genuineness": 3.8671910762786865, "identity": 0.6377161741256714, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/793869eb0b0f95e7cb933186e1a5a1ff037d25c597db264a7c1c8d01d5b33d8c.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "793c42ec0cd6369311676711ddfbc5a9f39195b7a4e1636ac0bd4714e92225e8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e06f146cbd16867867cee7e0c456cb62e0765f940129abbcca18584e6bf5de7a", "generation_seconds_batch": 22.635196528979577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1919925212860107, "target_z": 2.421874865187205, "ce": 5.95112943649292, "genuineness": 4.2751336097717285, "identity": 0.6710796356201172, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/793c42ec0cd6369311676711ddfbc5a9f39195b7a4e1636ac0bd4714e92225e8.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4f1255f6e09569c2dad16a116b35e0ed80459c749c478f868210ee700f0fda95", "generation_seconds_batch": 15.781331780017354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38812577724456787, "target_z": -0.08886718425930781, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.6315354108810425, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "798e53110bcd157cb894d6b372e279a62c87936ca12799821dbdbcfeb5832e2a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2ee28719ade2b5be63cd0955adcee09a530e9b02284342b8d20171fe28338cb4", "generation_seconds_batch": 22.959017605986446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7017502188682556, "target_z": 0.34765623185212374, "ce": 5.990842819213867, "genuineness": 4.268857479095459, "identity": 0.667961061000824, "hypothesis": "La porte 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_Elation/798e53110bcd157cb894d6b372e279a62c87936ca12799821dbdbcfeb5832e2a.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "79f93078c23188e9ceda34988d1b24dd823355febe60c66d9ed8adbb57686f6f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fb0913f6cadd16a199535762564819838b49ada21e4bd85479113038ba424fb2", "generation_seconds_batch": 23.901740805013105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7578798532485962, "target_z": 0.4257812007414787, "ce": 5.780362129211426, "genuineness": 4.042920112609863, "identity": 0.5930107831954956, "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_Elation/79f93078c23188e9ceda34988d1b24dd823355febe60c66d9ed8adbb57686f6f.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "7a0ea75ccef1a8fa365e4838d3d632011afcd723e33f9a238e6a8fa92c711580", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aa68f3be2ba0dcbc55ac61aa389af81a62bfa866d461cb2008b5048fadc4a1b1", "generation_seconds_batch": 24.378707362920977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3051440715789795, "target_z": 1.18750004148086, "ce": 6.09409761428833, "genuineness": 3.8797430992126465, "identity": 0.6248281002044678, "hypothesis": "De deur 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_Elation/7a0ea75ccef1a8fa365e4838d3d632011afcd723e33f9a238e6a8fa92c711580.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "7a162c143cde3eed527d2c5b3677efcb73a019693ba83da163a361340692fcf5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "23653f1944bb86d46d37aeb89e5504f9fa25d4248007c5e81e4b9d9b8d6aaaba", "generation_seconds_batch": 23.292100145015866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33690744638442993, "target_z": -0.1601562733329838, "ce": 6.268836498260498, "genuineness": 4.281409740447998, "identity": 0.4245675206184387, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7a162c143cde3eed527d2c5b3677efcb73a019693ba83da163a361340692fcf5.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": "7a3386b1b85924d176ed8d0170d1dff7706069482cd417901e402ba8ac3fcff1", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d41b0cf6d3599899e378ebed29a78904e0676ddca7fc587964f042a604a6f1fc", "generation_seconds_batch": 21.418959315982647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8383758068084717, "target_z": 1.9296875362957526, "ce": 6.054384231567383, "genuineness": 4.362998008728027, "identity": 0.6441769003868103, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand you're a moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7a3386b1b85924d176ed8d0170d1dff7706069482cd417901e402ba8ac3fcff1.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "7a595e37e4a95f9b2cc30fe70e5eb67bd236b0906897fcfb0ca9843bae3eae7b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f50ba012b80c6601c5a837e56aa3f2ae5e31104ab40f3bf793eb2d9d752f1c31", "generation_seconds_batch": 21.603425694047473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5035423636436462, "target_z": 0.07177731879667011, "ce": 6.252951145172119, "genuineness": 4.356721878051758, "identity": 0.5033248662948608, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7a595e37e4a95f9b2cc30fe70e5eb67bd236b0906897fcfb0ca9843bae3eae7b.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "7a83dcba15cd3d86801e4685a28048cdcf508566440226ee90d49b708403a9b7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7f730d4ff0d2de2e3052300cae1d44da293c2634124c30557910e44b2d35ad4a", "generation_seconds_batch": 21.48699527909048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8504937887191772, "target_z": 0.5546874533340325, "ce": 5.935244083404541, "genuineness": 4.080576419830322, "identity": 0.7032144665718079, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7a83dcba15cd3d86801e4685a28048cdcf508566440226ee90d49b708403a9b7.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "7af884dc41b6b3039c4fd068d75b4bc1627d98e1a9c1625ad8f0e1e3d15f181a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8936caed75fc6cb7f374a9f1a3201db459e86ce18b6bc60154c331e873429e17", "generation_seconds_batch": 22.86453713302035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.214444398880005, "target_z": 2.4531248859276347, "ce": 5.546053409576416, "genuineness": 3.672633647918701, "identity": 0.30976182222366333, "hypothesis": "The door is still open. I put your code on the chair. Tell me when you are ready!", "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_Elation/7af884dc41b6b3039c4fd068d75b4bc1627d98e1a9c1625ad8f0e1e3d15f181a.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "7b29a52239388eaffe19fe6b70bf9c8944bff0b395eac43aa5cfec0ca70fedeb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f387d6b0b82fb21259deda0613dc011aa144f36603034e33a69a6311f57265bb", "generation_seconds_batch": 22.542284039082006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6905242800712585, "target_z": 0.3320312214819087, "ce": 6.141753673553467, "genuineness": 3.9173994064331055, "identity": 0.5284433364868164, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7b29a52239388eaffe19fe6b70bf9c8944bff0b395eac43aa5cfec0ca70fedeb.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "7b4ba0271feced16bb66704f771c9bc9f2d17b8406c11b36d2fd3bce5221bf7b", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6a43b927499e99895723a205d9fcd02a8056060fb397327e36b5fcee5df55c80", "generation_seconds_batch": 17.590891978004947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19938981533050537, "target_z": -0.35156248444467747, "ce": 6.062326908111572, "genuineness": 4.174716949462891, "identity": 0.5328077077865601, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7b4ba0271feced16bb66704f771c9bc9f2d17b8406c11b36d2fd3bce5221bf7b.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "7bf38bb999bc3034c23767463f4641217e3fbc2efff38d2d14fe3bc3fb47b9ac", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "69e9f1ac3b677f85274c83ccae295dc5fcd0c8fea86ab0ee28b484aa40718b45", "generation_seconds_batch": 20.10488822706975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8439886569976807, "target_z": 1.9374998755574198, "ce": 6.062326908111572, "genuineness": 4.042920112609863, "identity": 0.5546380281448364, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7bf38bb999bc3034c23767463f4641217e3fbc2efff38d2d14fe3bc3fb47b9ac.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "7c8628591abbe6697b1c26ddd23b7b4d17bb131859c16efab3627102bcc36066", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fe51a375108dc7cb3d0b3fcf3af42f29fd84981d95625c852361d68e80b608d2", "generation_seconds_batch": 16.345627008005977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8645262718200684, "target_z": 0.5742187992585214, "ce": 6.38797664642334, "genuineness": 3.9676074981689453, "identity": 0.5008066296577454, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7c8628591abbe6697b1c26ddd23b7b4d17bb131859c16efab3627102bcc36066.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "7d0ab76259b242b60c8da9b014cf81ae38bdad84543e634b5d336d92192c6ba9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4488d67325ccaaaf730cea9e01ce58e24e7578cc38b06c9e497f94cecac8bd08", "generation_seconds_batch": 22.813902135007083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.034829616546631, "target_z": 2.203125051851075, "ce": 5.804190158843994, "genuineness": 3.961331605911255, "identity": 0.6890692710876465, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7d0ab76259b242b60c8da9b014cf81ae38bdad84543e634b5d336d92192c6ba9.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "7d370b7947c2863a7c155dafbee8dbdfb28aa81e02958154f20e8a5cda20c9bc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bb9dbcb6400ec087346cb052e178869dc4460879d73c577f4da00d8e50ef7e52", "generation_seconds_batch": 22.207357897073962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.372499704360962, "target_z": 1.2812501037021502, "ce": 6.221180438995361, "genuineness": 4.256305694580078, "identity": 0.4548627734184265, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7d370b7947c2863a7c155dafbee8dbdfb28aa81e02958154f20e8a5cda20c9bc.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": "7dbee2e2ea89df937cb522b41e52ebc306f86e44bd450b3f8277084d1ad9dbf7", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66d2120e50c12766423e15ee59c69c33061cfdd259cadff19fb8f73b76f858d4", "generation_seconds_batch": 16.486820703954436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9655596017837524, "target_z": 0.7148437266670162, "ce": 6.165581703186035, "genuineness": 4.582659721374512, "identity": 0.7628364562988281, "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_Elation/7dbee2e2ea89df937cb522b41e52ebc306f86e44bd450b3f8277084d1ad9dbf7.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": "7de94cee2722b1965a49fda866c96743be1179eedfe4ba735a09ad425ae68f8f", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The keys are on the kitchen table.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "676e0272fa3d4cc99e3dcde7562fdac92a7045be328d49fbf396cc7453860af2", "generation_seconds_batch": 23.48382224596571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1704328060150146, "target_z": 0.9999999170382798, "ce": 6.38003396987915, "genuineness": 4.030367851257324, "identity": 0.27305418252944946, "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_Elation/7de94cee2722b1965a49fda866c96743be1179eedfe4ba735a09ad425ae68f8f.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "7e852302911a0fe04eb17bcb5bfb7f64f5be133011cdb12c7cfc33e4a442f57d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9783fc5201442ab86e1d422ddcd411f2e86d1c8ede81e15cec58fd5fde91063a", "generation_seconds_batch": 22.960208195028827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25551944971084595, "target_z": -0.27343751555532253, "ce": 6.23706579208374, "genuineness": 4.281409740447998, "identity": 0.5317436456680298, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7e852302911a0fe04eb17bcb5bfb7f64f5be133011cdb12c7cfc33e4a442f57d.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "7ebd44d60316a30e1a8334871843d9c6fda6a479805852041d0c70f80883a765", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2624d93c547519d4336a6eb16bf1fd6b08a7d2891c5717c4aeb6fd7ad222933a", "generation_seconds_batch": 21.881187623017468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20219628512859344, "target_z": -0.3476562525925537, "ce": 6.046441555023193, "genuineness": 4.256305694580078, "identity": 0.5767219066619873, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7ebd44d60316a30e1a8334871843d9c6fda6a479805852041d0c70f80883a765.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "9ee3b8eb03e56247a0e08a7dfb1d30ab49293ef138235b81ef79346c32ec07c6", "generation_seconds_batch": 17.017267839983106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07029157876968384, "target_z": -0.53125002074043, "ce": 6.427689552307129, "genuineness": 3.9425034523010254, "identity": 0.3339206576347351, "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_Elation/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.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": "7fb78b3d1e10566220a11eeb45a29f6807e563e187fb04b2cdec12ee7b6b01f7", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fc6ba2701e4094b3dd68a78fd06d89846eb754b2950e5c1b1419fe5edd64a2f", "generation_seconds_batch": 26.622751284041442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2939181327819824, "target_z": 1.171875031110645, "ce": 6.038498878479004, "genuineness": 3.998987913131714, "identity": 0.7196176052093506, "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_Elation/7fb78b3d1e10566220a11eeb45a29f6807e563e187fb04b2cdec12ee7b6b01f7.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "7fcd40dfebf1dce4a9b7219d560388571ff0446130ee06e8eb86a5484071969e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "07105176e45d5185a66a7ef97a85a1a158682ff008c75ec20bb8b456df6c7451", "generation_seconds_batch": 26.3024123510113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1311421394348145, "target_z": 0.9453125466659675, "ce": 6.308549880981445, "genuineness": 4.557555198669434, "identity": 0.3123937249183655, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7fcd40dfebf1dce4a9b7219d560388571ff0446130ee06e8eb86a5484071969e.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "7fe58c96b986c3b1ac335e795559aa64e3c808a8a54652defb7b5787f50ae746", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "48056d38fc001867d92bdd4d10ec65b2b23911a96e204c6ba019be9c9b3bc99a", "generation_seconds_batch": 22.675372845027596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3558512330055237, "target_z": -0.1337890475928159, "ce": 5.990842819213867, "genuineness": 3.9676074981689453, "identity": 0.5530002117156982, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/7fe58c96b986c3b1ac335e795559aa64e3c808a8a54652defb7b5787f50ae746.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "8019f8fa39c643d60f15a21c7a2f76e682b74b3f0afe251734c17ff6d055d5fb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "568ec98ec84ce29acfbbf5938cc6e86835bc9362d92588f9a6ce30a76cf7899b", "generation_seconds_batch": 15.474798048031516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9553558826446533, "target_z": 3.484374906668065, "ce": 5.49045467376709, "genuineness": 4.005263805389404, "identity": 0.40848833322525024, "hypothesis": "La porte est encore ouverte! J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8019f8fa39c643d60f15a21c7a2f76e682b74b3f0afe251734c17ff6d055d5fb.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "802764ee112430a10fd8a22ae72051c828b2dd5611c744daa022f8bdfd51086c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "10d41d34508937ac181e281e96735cde64dbd885f1d1484cc14f7913ac04c1ac", "generation_seconds_batch": 18.371356523013674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5309056043624878, "target_z": 0.10986330231449926, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.41633784770965576, "hypothesis": "The 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_Elation/802764ee112430a10fd8a22ae72051c828b2dd5611c744daa022f8bdfd51086c.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "804e88a50ff7b980013eb18e526d8e84eca9d8ce41caf1d4b96526a5ad5b3b98", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "602303b44f2cedcf59f0d0a784d9a80001a2f75312191f466f3e210bb6f8f478", "generation_seconds_batch": 22.813902135007083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1807665824890137, "target_z": 2.40624985481699, "ce": 5.879645347595215, "genuineness": 3.835810661315918, "identity": 0.5824699401855469, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/804e88a50ff7b980013eb18e526d8e84eca9d8ce41caf1d4b96526a5ad5b3b98.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "8a3518e8e302eb3c10d2161b67b875589f304f77ceb7c4e20f6e13a7f0550399", "generation_seconds_batch": 17.446200608043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35514959692955017, "target_z": -0.13476563148138437, "ce": 6.292664527893066, "genuineness": 4.369274139404297, "identity": 0.6064993143081665, "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_Elation/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "80e3d131176d17b4c0231c26ea7320c7a486c2d28ddbe6352f97f94423834349", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47b0893c0597e07e113b0f4b37cbe129bdbbc1db992b6fda4086d54a75c51119", "generation_seconds_batch": 21.82300838199444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.034829616546631, "target_z": 2.203125051851075, "ce": 6.181467056274414, "genuineness": 3.8169827461242676, "identity": 0.3787633180618286, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/80e3d131176d17b4c0231c26ea7320c7a486c2d28ddbe6352f97f94423834349.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "80f64252b30228732913296b8804ca04ba3b97dbe3d23013b1e10ab033c19f89", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfba1fdf70907120a37fc9899596d4d3bce5080e093004b79485b89fb90e9891", "generation_seconds_batch": 18.122190579073504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18535739183425903, "target_z": -0.3710937474074463, "ce": 6.260893821716309, "genuineness": 4.093128204345703, "identity": 0.41768932342529297, "hypothesis": "The 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_Elation/80f64252b30228732913296b8804ca04ba3b97dbe3d23013b1e10ab033c19f89.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "812f2bbdd0a2ee1cfb1772c1bd09256631cb66f6f11a411a840145fd5320435e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cf5b3df489a896b8b09ce1cbfa25bdb8b825a814650fb43e7fb021320ee62308", "generation_seconds_batch": 23.798191750072874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44986841082572937, "target_z": -0.002929668703985282, "ce": 6.300607204437256, "genuineness": 3.7542223930358887, "identity": 0.3672025203704834, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/812f2bbdd0a2ee1cfb1772c1bd09256631cb66f6f11a411a840145fd5320435e.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "8133772525aa29d4e281245043613da1409391831cba6fed413d7c14be6c27d9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0745f49bf18b89bbe865c94f908ab320516905b640d8fa3ba1ee1382df95f5f8", "generation_seconds_batch": 21.453713039983995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5278782844543457, "target_z": 4.281249771855269, "ce": 5.220403671264648, "genuineness": 3.660081624984741, "identity": 0.4484255015850067, "hypothesis": "La puerta sigue abierta. dejado tu abrigo sobre la silla. Dime cuándo.", "wer": 0.2, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8133772525aa29d4e281245043613da1409391831cba6fed413d7c14be6c27d9.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "817e14db23fa69cfee5c3d6ebcb017f250e45c16ffea6758f94fbe4fae3c7ea5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e0e3fabe0878e1360ef11c4481177367831c1b60cf7eacdf6cb36eb679232e0f", "generation_seconds_batch": 22.735171312000602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011355459690093994, "target_z": -0.6132812422223387, "ce": 6.181467056274414, "genuineness": 4.645420074462891, "identity": 0.568228542804718, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/817e14db23fa69cfee5c3d6ebcb017f250e45c16ffea6758f94fbe4fae3c7ea5.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "81dc3eb50bc96b5edbacb5b4bc2ec83294bcd501f1014a64571106de0c14ba59", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "234401df75800cced506ca43ed00a86ea8bfa6b977987b60975d786b8699f124", "generation_seconds_batch": 15.054223940009251, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.726116418838501, "target_z": 1.7734374325936024, "ce": 6.141753673553467, "genuineness": 4.281409740447998, "identity": 0.5936852693557739, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/81dc3eb50bc96b5edbacb5b4bc2ec83294bcd501f1014a64571106de0c14ba59.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "81e0bcfd2de852806e9dd9f5fee94a219c868794441435426b12160677c53891", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e40cda8cb2f9ba048c09d4831b1dfca3d48cc25200f79f48ed5877ba4bb510f1", "generation_seconds_batch": 23.6200145840412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7634928226470947, "target_z": 0.4335937059265862, "ce": 5.990842819213867, "genuineness": 3.923675537109375, "identity": 0.30525052547454834, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/81e0bcfd2de852806e9dd9f5fee94a219c868794441435426b12160677c53891.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "822f5d42f730d4071d4a3b8586c43c1a84bb70ce62febafb55b740c9a08d771d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "80bf5478857ddd1f34d316d22d4a734064c676e881714b59273587f2b3c7c85b", "generation_seconds_batch": 27.50180923892185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5824747085571289, "target_z": 0.18164062111116938, "ce": 5.895530700683594, "genuineness": 4.168440818786621, "identity": 0.48459380865097046, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/822f5d42f730d4071d4a3b8586c43c1a84bb70ce62febafb55b740c9a08d771d.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "829c06b1e42f75da45838ed3e6abd524092709919f33e1a1443d1a8f6c655b20", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "57f7a66df0e5da468dcfbdbec492766e7b55b6a7657ccb94ca776e1f821dd077", "generation_seconds_batch": 18.591767744044773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.057281494140625, "target_z": 2.2343750725915053, "ce": 6.149696350097656, "genuineness": 4.20609712600708, "identity": 0.537850022315979, "hypothesis": "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_Elation/829c06b1e42f75da45838ed3e6abd524092709919f33e1a1443d1a8f6c655b20.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": "840252ee22dc6f3b6fd47010cea4fef420b903fa82220342a5d0188993f94b78", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b004e32064d6cd0db0274fa7070d4999c8491e67d8ae4dcd2f97a072a2bc78d", "generation_seconds_batch": 23.843906031921506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4959847927093506, "target_z": 1.453124885927635, "ce": 6.260893821716309, "genuineness": 4.256305694580078, "identity": 0.43134307861328125, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/840252ee22dc6f3b6fd47010cea4fef420b903fa82220342a5d0188993f94b78.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "845a140ce816d6a9dfe1f6392a8552d1612bb612fa79fbcfb505d6403b5e4303", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "19dd6cf9da682aeb914ddb5e5f6c34d4750d6aaf48ee14401d5c8a785ad43cce", "generation_seconds_batch": 23.412201669998467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.595233917236328, "target_z": 4.37499983407656, "ce": 5.34748649597168, "genuineness": 3.760498285293579, "identity": 0.6412311792373657, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay detrás.", "wer": 0.058823529411764705, "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_Elation/845a140ce816d6a9dfe1f6392a8552d1612bb612fa79fbcfb505d6403b5e4303.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": "8518257c96b9adc46ddff38ccf849e7472c8761492f2c3c692e7718d450a37b8", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Your message arrived after I had left.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ca379b44f00149482c73af2b154f18b56bca09aa7e86ad35faced1a9e4a318c", "generation_seconds_batch": 18.434494646964595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.383725643157959, "target_z": 1.296875114072365, "ce": 6.507116317749023, "genuineness": 4.118232727050781, "identity": 0.49027019739151, "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_Elation/8518257c96b9adc46ddff38ccf849e7472c8761492f2c3c692e7718d450a37b8.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "854219c5d3689244e32a9ea5c4f0129629eb52632663dfcade1ce0a38767c16d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d98e0e32952bbe9aff91417118fef7f4acad33a5ec8718e24c40e84368eaed6", "generation_seconds_batch": 20.298911933903582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6708788871765137, "target_z": 0.3046874533340324, "ce": 6.117925643920898, "genuineness": 4.162164688110352, "identity": 0.3579632639884949, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/854219c5d3689244e32a9ea5c4f0129629eb52632663dfcade1ce0a38767c16d.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "858e4b56d582014dea3bc79b50d6477bae235ec0f0f75fd32f0e5b97e80b1e67", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a1dd959ac9b4e18fbb0425e7b4306e35770eb54c3dff5c4f9b27686696508014", "generation_seconds_batch": 26.369793663965538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9441299438476562, "target_z": 3.46874989629785, "ce": 5.974957466125488, "genuineness": 4.017816066741943, "identity": 0.32442760467529297, "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_Elation/858e4b56d582014dea3bc79b50d6477bae235ec0f0f75fd32f0e5b97e80b1e67.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "87044c3bf29736eb24d41e36b9ab3fdd94ff14e310c0ea7c2b4aba0d1f5261e2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e3558f58e318ba7da4a5be421032fd1f019fdefc4ce49bedf1ee7bd64dad46a7", "generation_seconds_batch": 21.646729439031333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2583259344100952, "target_z": -0.26953126296276875, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.60094153881073, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/87044c3bf29736eb24d41e36b9ab3fdd94ff14e310c0ea7c2b4aba0d1f5261e2.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "87633e3b6ee65f6c2c33aac325037b356343ba4d213cba8e8ceaf2506f4b86bb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f908ac810da3dd7a5956899365f951310c9128e17788b41990a15b6580a79f2b", "generation_seconds_batch": 17.55173552199267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7485682964324951, "target_z": 1.8046874533340325, "ce": 6.356205940246582, "genuineness": 4.419482707977295, "identity": 0.6006594896316528, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/87633e3b6ee65f6c2c33aac325037b356343ba4d213cba8e8ceaf2506f4b86bb.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": "8770126ecbd20fe7f0fcd9be153aa1950dea3ead0287666714da69d9395dbbd4", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c9086dde712c206aa581bc022237c6b0787dda0f995e6efa08c00b2349ac5dd", "generation_seconds_batch": 15.244649747037329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5473936796188354, "target_z": 0.1328125051851075, "ce": 6.23706579208374, "genuineness": 3.9927117824554443, "identity": 0.5529588460922241, "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_Elation/8770126ecbd20fe7f0fcd9be153aa1950dea3ead0287666714da69d9395dbbd4.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "879f0d87b8b0b0aaeffff3c153dfed61a57931e04a2382daf6cdb4cf03a63938", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e6f9882fbf0b1984adebcbaa6f55e0a7dbf3444f0df96889c818ab6b2f03e0ca", "generation_seconds_batch": 16.345627008005977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7606863975524902, "target_z": 0.42968753629575257, "ce": 6.41180419921875, "genuineness": 4.030367851257324, "identity": 0.43279916048049927, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/879f0d87b8b0b0aaeffff3c153dfed61a57931e04a2382daf6cdb4cf03a63938.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "87fe304f706868c05ad2aa6caf4c9d5b821f70c41a65d3cf51eaf02b21e1319b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aa0bbe0fa6f0701296872fcb6518308478830ee3a4c78497b680494ce4a9b783", "generation_seconds_batch": 21.029314663959667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19377684593200684, "target_z": -0.359374989629785, "ce": 6.006728172302246, "genuineness": 4.174716949462891, "identity": 0.5011265277862549, "hypothesis": "La porte 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_Elation/87fe304f706868c05ad2aa6caf4c9d5b821f70c41a65d3cf51eaf02b21e1319b.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "880746e0af176a3168a1891d45341c90c01908ee351081f63545867bbc673e0c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "91d4dc358227563736122411fb0c663c8963a0f918be810542f5a70fcfbaca09", "generation_seconds_batch": 23.427314288099296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33831071853637695, "target_z": -0.15820310555584685, "ce": 5.998785495758057, "genuineness": 4.319066047668457, "identity": 0.40879496932029724, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/880746e0af176a3168a1891d45341c90c01908ee351081f63545867bbc673e0c.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "88417e4fda44347005c6ad651414cc97f9852867a749b5ed7d51c8ac28639b14", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5e7e042ffb6c75321adc9b581e2c6442ad62a7c043ce1ca8677f289e6fb78ff0", "generation_seconds_batch": 24.42343245598022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.068507432937622, "target_z": 2.25000008296172, "ce": 6.109982967376709, "genuineness": 4.3127899169921875, "identity": 0.14364947378635406, "hypothesis": "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_Elation/88417e4fda44347005c6ad651414cc97f9852867a749b5ed7d51c8ac28639b14.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "8844265090f2c2f5280bded655c676f41a13b67617f0b9ba22f377a4b1168377", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b208a34a7b50a31eb837b97bed7a2694715e50ced60b6adb989bf06d886dfd8b", "generation_seconds_batch": 22.907866170979105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8925910592079163, "target_z": 0.6132812422223387, "ce": 5.935244083404541, "genuineness": 4.080576419830322, "identity": 0.3101080358028412, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8844265090f2c2f5280bded655c676f41a13b67617f0b9ba22f377a4b1168377.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": "884932282e055c06c76be8551347b451c82b4c741eb38ebfc3b190f558b89442", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ae28202def06181d8eea4b4ddcc7eba605bd1b31dbb76bf53247927fe74f9dc", "generation_seconds_batch": 22.946684169000946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3491556644439697, "target_z": 2.640625010370215, "ce": 5.9431867599487305, "genuineness": 3.911123275756836, "identity": 0.45831313729286194, "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_Elation/884932282e055c06c76be8551347b451c82b4c741eb38ebfc3b190f558b89442.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "88f237ba0810dc9b8d48f65bba18f99b92eced7eaaee212574eee57ce3c54d9b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "798b0541391d2400105d90e03e0fc4902de0e46183ba77984ea2590116eecada", "generation_seconds_batch": 20.339327460038476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5319580435752869, "target_z": 0.11132815740692192, "ce": 6.292664527893066, "genuineness": 4.413206577301025, "identity": 0.7120962142944336, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/88f237ba0810dc9b8d48f65bba18f99b92eced7eaaee212574eee57ce3c54d9b.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "8968c83e92e4d675ab122997abfb26c332051a1c313bd4de911dbc14af8ebd48", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "200aaeb1f81669402f82b387cb50c4ff541668a662ef5aac76e1e17cf034c496", "generation_seconds_batch": 16.4094361619791, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0946578979492188, "target_z": 0.8945313459244889, "ce": 5.998785495758057, "genuineness": 4.20609712600708, "identity": 0.5530161261558533, "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_Elation/8968c83e92e4d675ab122997abfb26c332051a1c313bd4de911dbc14af8ebd48.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "89fe14f7778598e4b1353e9eba7ff60831195fd8289998d55e4d7229f9fb287a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7beb84b06df06d0667fd0733e2a7bded57a52025a2b54075fc139fc637acc74b", "generation_seconds_batch": 23.557680501951836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1760458946228027, "target_z": 1.0078125881468276, "ce": 5.967014789581299, "genuineness": 3.5439748764038086, "identity": 0.3526664972305298, "hypothesis": "The 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_Elation/89fe14f7778598e4b1353e9eba7ff60831195fd8289998d55e4d7229f9fb287a.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": "8acc696bb74c9ff13c20a3b57fede8170a70d79abbafd06f592f51039878a51d", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8decafbb05dc4874895f5d1d102e73dc23d9c45976db9b827c0a58b7785ba129", "generation_seconds_batch": 23.592388552962802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.644217312335968, "target_z": 0.2675780951856318, "ce": 6.221180438995361, "genuineness": 4.074300289154053, "identity": 0.49145710468292236, "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_Elation/8acc696bb74c9ff13c20a3b57fede8170a70d79abbafd06f592f51039878a51d.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "8af75bcb879b436164be175e5b3ee0af06e376f347d725b62c34d252ec82bc4a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2f583ffd8eca7d0340fb0120d817d0a0f2042950ee440c681b2f480c8d26fa12", "generation_seconds_batch": 27.290725592058152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6147492527961731, "target_z": 0.22656248444467747, "ce": 6.109982967376709, "genuineness": 3.9676074981689453, "identity": 0.5067209601402283, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8af75bcb879b436164be175e5b3ee0af06e376f347d725b62c34d252ec82bc4a.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "8b034e788ae1704ea564f26d1c903c7538edd8f24864a7562747df858a191100", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6611c1732219cbef851a895797fa73d0f3ef9eb8552d87f87a4b69f134c5dd76", "generation_seconds_batch": 23.64345809200313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2456967681646347, "target_z": -0.28710937888883065, "ce": 6.316492557525635, "genuineness": 4.356721878051758, "identity": 0.449712336063385, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8b034e788ae1704ea564f26d1c903c7538edd8f24864a7562747df858a191100.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": "8b1e857ba9d3dae76d2d3e6c8a4795dea642cbc5892b02c6acdbce2f5ad24093", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Your message arrived after I had left.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75650f858a98f26802b341e0a731fdac698a3dd0a4530132d79aaae9eaff1229", "generation_seconds_batch": 22.064946958096698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019774913787841797, "target_z": -0.6015624844446775, "ce": 6.41180419921875, "genuineness": 4.281409740447998, "identity": 0.373932421207428, "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_Elation/8b1e857ba9d3dae76d2d3e6c8a4795dea642cbc5892b02c6acdbce2f5ad24093.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": "8b64ce416dfbcad4eb3b94e672de899a1058780f62762a422b26b4706320c4ea", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92a432bd12c815379f51434ca8cb3b9a5c1c464ca12fb524e6192aed3e4d15bf", "generation_seconds_batch": 16.655406868085265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13343745470046997, "target_z": -0.44335937888883065, "ce": 6.308549880981445, "genuineness": 4.419482707977295, "identity": 0.4767935276031494, "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_Elation/8b64ce416dfbcad4eb3b94e672de899a1058780f62762a422b26b4706320c4ea.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "8b80be1bc10a109112be54a98e98bf492ae1ceda4e629b043a6fdc875087534e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0c79090e07b9fddc15193106c0c98c5bbd69e6c85cff357c4004483cabb826e8", "generation_seconds_batch": 20.19735898997169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7087664604187012, "target_z": 0.3574219048143682, "ce": 5.998785495758057, "genuineness": 3.7416701316833496, "identity": 0.4785599112510681, "hypothesis": "The 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_Elation/8b80be1bc10a109112be54a98e98bf492ae1ceda4e629b043a6fdc875087534e.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "8c0aaee027835c68c9566edfe10584261db04a7cb37574472984e78789798fe2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d4fb13507642a326ec5ac247d204c2a058394dd1f1ee7043762719229195136b", "generation_seconds_batch": 24.44640030199662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3379297256469727, "target_z": 2.625, "ce": 6.1020402908325195, "genuineness": 4.086852550506592, "identity": 0.5313544273376465, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8c0aaee027835c68c9566edfe10584261db04a7cb37574472984e78789798fe2.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": "8c428d8bf8305dadbf8b03be9290a1765f1a0c061b9f037c2f761e2084d37dc8", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fdef649f0b5152bdb7a861e52a10750ef163e8623460c8680d43e40509cfa9bb", "generation_seconds_batch": 16.364956358913332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17413145303726196, "target_z": -0.38671875777766124, "ce": 6.133810997009277, "genuineness": 4.344170093536377, "identity": 0.5097611546516418, "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_Elation/8c428d8bf8305dadbf8b03be9290a1765f1a0c061b9f037c2f761e2084d37dc8.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "8d30357b76ee7b9d2092ba8e61d6c487a7fa588bfdda51b4b743462c6c07e6cf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c196d62123e91689a98ed9e73ca09db38cafab3ad0ce400ca2041962ae0f41d9", "generation_seconds_batch": 20.01161761197727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9206559062004089, "target_z": 0.6523437681478763, "ce": 6.1894097328186035, "genuineness": 4.268857479095459, "identity": 0.2458895593881607, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8d30357b76ee7b9d2092ba8e61d6c487a7fa588bfdda51b4b743462c6c07e6cf.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "8ea6b8de0cb450e36dbd1bdfc6e09784d01d800091fbc952ae31ade1aa5e53ef", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3c442698125fb436f4d465d9a2b1765cd2ebbf4134ba65809a60ff59f3b9b0ac", "generation_seconds_batch": 22.461153862066567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0020439624786377, "target_z": 0.7656250933319352, "ce": 6.427689552307129, "genuineness": 4.375550270080566, "identity": 0.47816985845565796, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8ea6b8de0cb450e36dbd1bdfc6e09784d01d800091fbc952ae31ade1aa5e53ef.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "8ef7929a379aa0d98e1c78b3963caaf8a625b0b5256292dff1f97d4b87a334dd", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e4c64d3686f74dee7e06f1eba29f1bbf70e5016386016f1440a2a55d6e3c49ee", "generation_seconds_batch": 28.007873861002736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1134111881256104, "target_z": 2.3125001244425802, "ce": 6.054384231567383, "genuineness": 4.042920112609863, "identity": 0.4480372965335846, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8ef7929a379aa0d98e1c78b3963caaf8a625b0b5256292dff1f97d4b87a334dd.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "8f7ef220650809c967c0425f426a525939c35daaf0a7e1ac9111b43fb32c58fd", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c69ab980c76c270e468da5d94b663cbd8dc5da32a03a4eb9fd22d09b09e1710e", "generation_seconds_batch": 22.930367987952195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.248122215270996, "target_z": 2.49999991703828, "ce": 5.645336627960205, "genuineness": 3.973883628845215, "identity": 0.6125394105911255, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8f7ef220650809c967c0425f426a525939c35daaf0a7e1ac9111b43fb32c58fd.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "8ff0011f5df6f600a6b12e1d13659606a46d7e04ecb167900c320f4f0c307609", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cbdc0043c89105da3b49530ae70caf8166cd35dc35087073af916f30ea7afa36", "generation_seconds_batch": 22.944198927958496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8533003330230713, "target_z": 0.5585937888883064, "ce": 6.006728172302246, "genuineness": 4.143336772918701, "identity": 0.5060721039772034, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/8ff0011f5df6f600a6b12e1d13659606a46d7e04ecb167900c320f4f0c307609.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "8ff6e4e99ae6703c998872250bcfa549c2989193fe5f524b03fe1e1c5357d5c0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0f6abcf2bf7f2421696c975edf6ad1a590383fbf13f4388722bfebcbcada3fcc", "generation_seconds_batch": 23.879590797936544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5445871949195862, "target_z": 0.12890625259255376, "ce": 6.046441555023193, "genuineness": 4.030367851257324, "identity": 0.675894021987915, "hypothesis": "La porte 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_Elation/8ff6e4e99ae6703c998872250bcfa549c2989193fe5f524b03fe1e1c5357d5c0.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "900f97342faa2509f6a246365fd08547529605ab35cbe5155d49e64ae6af5012", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2e59f42fc68d46fb271cad6a8b9171132673bc42497f8c474c5f0cbebb896e54", "generation_seconds_batch": 16.814932734007016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7634928226470947, "target_z": 0.4335937059265862, "ce": 6.006728172302246, "genuineness": 3.6914620399475098, "identity": 0.3734299838542938, "hypothesis": "The 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_Elation/900f97342faa2509f6a246365fd08547529605ab35cbe5155d49e64ae6af5012.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "9062f0be0fd4a63ef904550be9cbf1bc54e72ecf16b82b47fc39c033ea5ddd90", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "517a1ca2245f21eaac0e750e071968ebf3cfc464b97b09289f1bb03c2ce1d66f", "generation_seconds_batch": 21.68981385801453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7869670391082764, "target_z": 3.25000008296172, "ce": 6.292664527893066, "genuineness": 4.13078498840332, "identity": 0.4555891156196594, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9062f0be0fd4a63ef904550be9cbf1bc54e72ecf16b82b47fc39c033ea5ddd90.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "90730572159e5f5556a960ff98026920f24ead2f4e66e0a50011cce5cc681ed0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "328512226426ce02551a168e83152699155b09025a4a67f9308801aaf14dc87e", "generation_seconds_batch": 22.147753575001843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7817350029945374, "target_z": 0.45898438925904567, "ce": 6.078212261199951, "genuineness": 3.8922953605651855, "identity": 0.6427127122879028, "hypothesis": "Ik 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_Elation/90730572159e5f5556a960ff98026920f24ead2f4e66e0a50011cce5cc681ed0.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "90a1ca49246439aea105f6f7858e535cfa1c37d88c1e972a2fc3a0b8356c297a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dac1e1d28a0990ffbf26597d50f0453c78dcca8ad1b52e23b53a8bd1f064a1d8", "generation_seconds_batch": 22.33032385597471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22745463252067566, "target_z": -0.3125, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.6807606220245361, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/90a1ca49246439aea105f6f7858e535cfa1c37d88c1e972a2fc3a0b8356c297a.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": "90a5f8bc2af836043f2fe3399356c19b1cc5ff09af7d12115f10f4b46b4e84db", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "942279c6b43faa861e8d9cde651ee746696ebe8a802b6c62bde4b77277ef4086", "generation_seconds_batch": 18.153539462946355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3158588409423828, "target_z": -0.18945312629627686, "ce": 6.308549880981445, "genuineness": 3.911123275756836, "identity": 0.5835622549057007, "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_Elation/90a5f8bc2af836043f2fe3399356c19b1cc5ff09af7d12115f10f4b46b4e84db.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "9123f50234d16812dfdcbcef8e912273af69678ce4d2086527ec020dd70e5b82", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7a3196ef6900b919aea23357ceba94f58b7e596177c2b9501c0246ddbdc39008", "generation_seconds_batch": 16.057577850995585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9178494215011597, "target_z": 0.6484375155553225, "ce": 6.23706579208374, "genuineness": 4.262581825256348, "identity": 0.47562021017074585, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9123f50234d16812dfdcbcef8e912273af69678ce4d2086527ec020dd70e5b82.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "913f682f2ae9968416075f9ab7c4383275dcc9a32b5b4146a9ce079e3b20d2d8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c83a62b9497e3ca5b98bdb0a70df3af186cc688de36349b56018d1113ff1922a", "generation_seconds_batch": 21.81650149205234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40601709485054016, "target_z": -0.06396485509242268, "ce": 6.24500846862793, "genuineness": 4.362998008728027, "identity": 0.6701453924179077, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/913f682f2ae9968416075f9ab7c4383275dcc9a32b5b4146a9ce079e3b20d2d8.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "914b029e5621af7531f0c6ba8205a148dcb9eb26390efc5b7376a0d03949b338", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cfa335d724911a368ef0a55c163a96f84db593fac70efb4fd543bfe2614f75eb", "generation_seconds_batch": 16.68467323400546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09274345636367798, "target_z": -0.5, "ce": 6.046441555023193, "genuineness": 4.344170093536377, "identity": 0.5526800751686096, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/914b029e5621af7531f0c6ba8205a148dcb9eb26390efc5b7376a0d03949b338.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "915879144284ebf303376e960ac468208b616d792802a5404c549e0748191467", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "96801c3ab879e62ce34f874de8126fef93a16714b24f4c6afe6a5b4673c05b84", "generation_seconds_batch": 16.924429086968303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5586196184158325, "target_z": 0.14843751555532253, "ce": 6.09409761428833, "genuineness": 4.268857479095459, "identity": 0.6305586099624634, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/915879144284ebf303376e960ac468208b616d792802a5404c549e0748191467.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": "917281f00902e46d833c0939bb857ff4318341baaa93af2dfe23ce4465e56c6d", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d7cf6007e7ea6c2a863361d34dc54804d151af70f2909714d5db06d46299fa7d", "generation_seconds_batch": 23.599875299958512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5296626091003418, "target_z": 1.4999999170382798, "ce": 6.078212261199951, "genuineness": 4.074300289154053, "identity": 0.6587895154953003, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houtenhek. Ik wacht aan de andere kant.", "wer": 0.14285714285714285, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/917281f00902e46d833c0939bb857ff4318341baaa93af2dfe23ce4465e56c6d.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "9201264c00fd6d99813a76f8d7d0fccd26661466e3bcb349d3011894c6936e02", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e52ac238e7a10fa76488cb45e60257f2f9edd4eadcdd788044daa94d67cffed2", "generation_seconds_batch": 24.6816872790223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2930259704589844, "target_z": 2.56249995851914, "ce": 6.2767791748046875, "genuineness": 4.319066047668457, "identity": 0.3961442708969116, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9201264c00fd6d99813a76f8d7d0fccd26661466e3bcb349d3011894c6936e02.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "9210e830f913ef21a802fd3670dfab6aee608fa95c27a3c5bde80a661bbb6247", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6fea2715a47287b335ece93f78e0f9648efd7149a1ad6321029a5884cce9b83e", "generation_seconds_batch": 24.316638897988014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22745463252067566, "target_z": -0.3125, "ce": 6.157639026641846, "genuineness": 3.6914620399475098, "identity": 0.2844383120536804, "hypothesis": "The 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_Elation/9210e830f913ef21a802fd3670dfab6aee608fa95c27a3c5bde80a661bbb6247.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "92261c7f7a2797ff5bfd6d75672918017ceb358cb352b375b4f9770e0a87677b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b614272ab92c81de1f18bc8f06e6c0886ab3c1e882ab838292d7ff265b0b7bd6", "generation_seconds_batch": 21.959386009024456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.035721778869629, "target_z": 0.8125001244425802, "ce": 5.816103935241699, "genuineness": 3.9927117824554443, "identity": 0.4331153631210327, "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_Elation/92261c7f7a2797ff5bfd6d75672918017ceb358cb352b375b4f9770e0a87677b.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "92649c0c3678353bc51af9d64b7ba2fe4a978c49c68f98c689531d206d77ad60", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "179b9a88ce288bca3055dae25d1b54a28e5705353513c69a3350198bd802f276", "generation_seconds_batch": 22.391288143000565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1021852493286133, "target_z": 2.2968751140723653, "ce": 5.315715789794922, "genuineness": 3.986435890197754, "identity": 0.5634055733680725, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/92649c0c3678353bc51af9d64b7ba2fe4a978c49c68f98c689531d206d77ad60.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "92d64b4c1914f23e31b44890eeb22f8502cf407a018a80d2b3b0b98c12f0ef11", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "36a30ff2eba0683fc01212a7ea1f9fd6ef4fc3c35cee9e76d8db1373c2073af4", "generation_seconds_batch": 23.43631756096147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1881638765335083, "target_z": -0.3671874948148925, "ce": 6.133810997009277, "genuineness": 4.319066047668457, "identity": 0.5795451402664185, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/92d64b4c1914f23e31b44890eeb22f8502cf407a018a80d2b3b0b98c12f0ef11.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": "930d79a5c4b363b5439e832af93c5460fcbfdea972de7899ffb2ff3ff57007e7", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Someone moved the little blue chair.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c3f014317b86be0aa1f96b98ec23142a64f17ea4c7e686fbcf56231b89ef724", "generation_seconds_batch": 20.75479608005844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8982040286064148, "target_z": 0.6210937474074463, "ce": 6.459460258483887, "genuineness": 4.105680465698242, "identity": 0.39351576566696167, "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_Elation/930d79a5c4b363b5439e832af93c5460fcbfdea972de7899ffb2ff3ff57007e7.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "9351b4b806cd75de936a4ded601d419b31bb43fa1d69fa4d894267e59998f6dc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8ca15acc67dcb7850ef6b805f6c4e7135f4d8dab87afa2f5b1a2ead8bef39f04", "generation_seconds_batch": 17.26491684000939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1134111881256104, "target_z": 2.3125001244425802, "ce": 5.760505676269531, "genuineness": 3.9173994064331055, "identity": 0.5329296588897705, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9351b4b806cd75de936a4ded601d419b31bb43fa1d69fa4d894267e59998f6dc.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "9382643d18e9a79c66bf3f42793aacd37eb8de292763cae168ae169206a07db3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "74e02ca54c1b781411fb00542b6a953a839afd77fdfe58cfc57f078c10af9a39", "generation_seconds_batch": 17.3771092799725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.259348154067993, "target_z": 2.5156249274084947, "ce": 5.959072113037109, "genuineness": 4.13078498840332, "identity": 0.5261982679367065, "hypothesis": "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_Elation/9382643d18e9a79c66bf3f42793aacd37eb8de292763cae168ae169206a07db3.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "9408539c780fa0f34f43499f9a086a9bb866729afb3d49e630c801f784e0d9d3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "79d24fc069a289a622cc5619bc019850e5e689ef3ecf79ab2bbd8224f4015ac5", "generation_seconds_batch": 22.147753575001843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4959847927093506, "target_z": 1.453124885927635, "ce": 6.125868320465088, "genuineness": 3.6412534713745117, "identity": 0.6890423893928528, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9408539c780fa0f34f43499f9a086a9bb866729afb3d49e630c801f784e0d9d3.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "941fd40dcc62ff6d03a560bf0a58d7941c7dfc2bda60addbf2cee0f688462dd3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bf51abfef999a4bfb602fea03c11ce7c9b9561b034178c479696861c8338481d", "generation_seconds_batch": 23.96982458990533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209723711013794, "target_z": 1.0546876192574728, "ce": 6.09409761428833, "genuineness": 4.111956596374512, "identity": 0.7418705821037292, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/941fd40dcc62ff6d03a560bf0a58d7941c7dfc2bda60addbf2cee0f688462dd3.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "942bbf854fdb93ae96c32de0fb2b2df45442a9c999e205c30c26447e8a30fe2f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "40774c8e65d13fcdf3a449339fcf1a5bdda246f1371dcb484f9b82384e5b6f76", "generation_seconds_batch": 23.255221355939284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25551944971084595, "target_z": -0.27343751555532253, "ce": 6.324435234069824, "genuineness": 4.168440818786621, "identity": 0.3478242754936218, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/942bbf854fdb93ae96c32de0fb2b2df45442a9c999e205c30c26447e8a30fe2f.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "948ed715d155cefbaa99293fe0e86fc3b66a6e761a1138c41a274f27e376d3bf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fb7cc7d5d00720a958fe84e67e50c3a514f3eb06ffdb7c3ca6aae6460e68c809", "generation_seconds_batch": 26.74647353508044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.539996385574341, "target_z": 2.90624985481699, "ce": 5.454712867736816, "genuineness": 4.055472373962402, "identity": 0.4667488932609558, "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_Elation/948ed715d155cefbaa99293fe0e86fc3b66a6e761a1138c41a274f27e376d3bf.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "9494d6677566bd6c0be4d17ba88ea46115bb4343d7538544d4db4b25e6e8e99e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3065adbfbe928be246c7abd93a373a0c8638a2acf7290ed6819599899e7a781e", "generation_seconds_batch": 15.054223940009251, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38812577724456787, "target_z": -0.08886718425930781, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.7260999083518982, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9494d6677566bd6c0be4d17ba88ea46115bb4343d7538544d4db4b25e6e8e99e.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": "94a16a623692a71189a2858997751a8c40203dee9c8f7369ea03a9dcd33bec90", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1b3c77ea1263945d4ad476c84add9ee94986b4e49738c2b2bfeb83cfc74c81c", "generation_seconds_batch": 16.7114627660485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21482546627521515, "target_z": -0.33007811592606184, "ce": 6.213237762451172, "genuineness": 4.331617832183838, "identity": 0.6191445589065552, "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_Elation/94a16a623692a71189a2858997751a8c40203dee9c8f7369ea03a9dcd33bec90.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "94abc6c115821aa0ad5305a1bae4fe584e86d29989978893b7d67c148734a910", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bda685e9201290726e56a99d293287f6c2afbd4651e53672c23e51a9c7eadc09", "generation_seconds_batch": 23.416820472921245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4505700170993805, "target_z": -0.001953126296276877, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.6186344623565674, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/94abc6c115821aa0ad5305a1bae4fe584e86d29989978893b7d67c148734a910.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "9507ee3d403536ff77f144d7158875829143eae8331035a184da3ef75b5c4584", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "98b0df482a3aab5cd9c6af98a8bc1bec9fbf46d4ea7bbfc862563fbdee67f30e", "generation_seconds_batch": 21.023585665039718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6747076511383057, "target_z": 3.09374997925957, "ce": 6.23706579208374, "genuineness": 4.005263805389404, "identity": 0.44161829352378845, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9507ee3d403536ff77f144d7158875829143eae8331035a184da3ef75b5c4584.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "951ff52eedc02a34f06cd9e0566cf3c1b0572657fde83a6bb5176c5ef6be43d2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dbcacdefffe75311864a7c32bbde7c293991069d5b9944a1c224f42e8e81454b", "generation_seconds_batch": 15.85167281597387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6699867248535156, "target_z": 1.6953123807425272, "ce": 6.1020402908325195, "genuineness": 4.18099308013916, "identity": 0.554976224899292, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro de la caja.", "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_Elation/951ff52eedc02a34f06cd9e0566cf3c1b0572657fde83a6bb5176c5ef6be43d2.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "954159c4fef6cc237f56c3cef2542df058079099bee830633a8cce7702f88cbe", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "17adebd6c0ce6b29e43fffb0d21ba71ff512383c5860913ebdd15818e7e3ba36", "generation_seconds_batch": 17.55173552199267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7410410046577454, "target_z": 0.40234376814787626, "ce": 6.205295085906982, "genuineness": 4.281409740447998, "identity": 0.5931640863418579, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/954159c4fef6cc237f56c3cef2542df058079099bee830633a8cce7702f88cbe.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": "955c70bbbff6ff95346ffb286ed14aa2bf6910dfe7d37364270690b5e9cf3790", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The keys are on the kitchen table.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d85de3be1c02559e9361c0f3081937696f2d0a1fe0a40ff07f4b0acab45655a3", "generation_seconds_batch": 16.107184757012874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21482546627521515, "target_z": -0.33007811592606184, "ce": 6.395919322967529, "genuineness": 4.375550270080566, "identity": 0.6564990282058716, "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_Elation/955c70bbbff6ff95346ffb286ed14aa2bf6910dfe7d37364270690b5e9cf3790.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "96b5f0cf92cc5c8ac84ac61c35473e1fc2cce4efd12bf5ee9dd1785a6bcaa231", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c9a2bdec327e7dc61344638bc9a138fbf1b841115ff3eae214368fd54094b89f", "generation_seconds_batch": 21.71621260093525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1030772924423218, "target_z": 0.90625002074043, "ce": 6.221180438995361, "genuineness": 4.482243061065674, "identity": 0.572686493396759, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/96b5f0cf92cc5c8ac84ac61c35473e1fc2cce4efd12bf5ee9dd1785a6bcaa231.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "96c948082e05c64fd83fb3eabc75f071328873bd0f6422a59218503e5db3cf6c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6e75bea0ed25c17580f89ae93c43c8ed80fc504fcca5afe44102ff50ff96024d", "generation_seconds_batch": 22.992220995016396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4930180609226227, "target_z": 0.05712889231502357, "ce": 6.300607204437256, "genuineness": 4.3127899169921875, "identity": 0.507530927658081, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/96c948082e05c64fd83fb3eabc75f071328873bd0f6422a59218503e5db3cf6c.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "97064e34b0b25e114ebc884803a30c8345c0e4afa200de4b9149e72266d8bb47", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cb7670205ec14774141dfc95c4be49cf031c99e0acbfaf410fae37053f972f9a", "generation_seconds_batch": 26.3024123510113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41619059443473816, "target_z": -0.04980469981463033, "ce": 6.348263263702393, "genuineness": 4.406930446624756, "identity": 0.41900157928466797, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/97064e34b0b25e114ebc884803a30c8345c0e4afa200de4b9149e72266d8bb47.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "974a2bfed1527cc04fd9784169e971e0d8d3374ae3fe1e477f602a1bbcf36cd4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2a097a6098341503ddbe2ba8e41fe8eb432c34422595c00f6ed768ef2cb64084", "generation_seconds_batch": 16.924429086968303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43987029790878296, "target_z": -0.016845709120280557, "ce": 6.117925643920898, "genuineness": 4.250029563903809, "identity": 0.5069238543510437, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/974a2bfed1527cc04fd9784169e971e0d8d3374ae3fe1e477f602a1bbcf36cd4.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "975bfa9b4ff8636d26b5ce3aec636a83347c3777cdb74d46de806db256594e15", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b3f32c2c06baaf0bb25b50cedc0f9f38613f5a801a3a02633ef35348c43ba588", "generation_seconds_batch": 17.26491684000939, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.056389331817627, "target_z": 3.625, "ce": 5.692992687225342, "genuineness": 3.8169827461242676, "identity": 0.15294179320335388, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/975bfa9b4ff8636d26b5ce3aec636a83347c3777cdb74d46de806db256594e15.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "97c9b06b84e8217c5dc79809aaa741d43b195d7da4cebeae9b3ac59d80796785", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8a2cbec74ec1af9a1c35c0eff3cc5ae8be907e0234a7de05c3bce532acef8d2e", "generation_seconds_batch": 20.19735898997169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9262688159942627, "target_z": 0.6601561903712636, "ce": 5.919358730316162, "genuineness": 3.6287014484405518, "identity": 0.43409308791160583, "hypothesis": "The 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_Elation/97c9b06b84e8217c5dc79809aaa741d43b195d7da4cebeae9b3ac59d80796785.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "97fa4e9884154e07c21083c34e64c184728644d7180a860172155d0507f7a4ae", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f43cb60e3248a11ae50eabb75fb6282c50b1f33bb5c90e9f7dd896f59a5c02a", "generation_seconds_batch": 22.34854559705127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6185779571533203, "target_z": 3.0156249274084947, "ce": 5.5539960861206055, "genuineness": 3.810706615447998, "identity": 0.41789036989212036, "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_Elation/97fa4e9884154e07c21083c34e64c184728644d7180a860172155d0507f7a4ae.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "98713d00a61ec1cb261c7b76c6f998f192df34b6353ac4d166a927c241c72719", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9d93eba2607349b62200903bfa819b3328dc2647d518746e6726c84b5907458a", "generation_seconds_batch": 22.391288143000565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1134111881256104, "target_z": 2.3125001244425802, "ce": 5.9431867599487305, "genuineness": 3.961331605911255, "identity": 0.4600412845611572, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/98713d00a61ec1cb261c7b76c6f998f192df34b6353ac4d166a927c241c72719.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "9875b58515856c4e9bb3d6c5679fa0fe7441f51e6c9f3929f4a8b70080ba37df", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "278f3a37edf2e2fe9fc512a9a0308ea9910d5c3e7db40cb563b2ff1647f25a43", "generation_seconds_batch": 19.97298199904617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.034829616546631, "target_z": 2.203125051851075, "ce": 6.133810997009277, "genuineness": 4.086852550506592, "identity": 0.5127029418945312, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9875b58515856c4e9bb3d6c5679fa0fe7441f51e6c9f3929f4a8b70080ba37df.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "98ac8914d24ea5386cf1e542c91b908ff4fce2631d1014e59d0ce9046935fd53", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f44b8fa0204c108e3a20086e865117304fba603434875441234e18fc270b9c12", "generation_seconds_batch": 23.57665981503669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38146036863327026, "target_z": -0.09814454453683799, "ce": 6.268836498260498, "genuineness": 4.137060642242432, "identity": 0.3394430875778198, "hypothesis": "The 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_Elation/98ac8914d24ea5386cf1e542c91b908ff4fce2631d1014e59d0ce9046935fd53.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "98cf12ee5b532dae0840fa6257ed436112b74189678abf9bad55f2db32e07df9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3ac289286466ef3c837bc742e1efe91e6ccf1d61e8916d122fc0f9efa4fe1970", "generation_seconds_batch": 22.68844109599013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6428140997886658, "target_z": 0.265625010370215, "ce": 5.788304805755615, "genuineness": 4.243753433227539, "identity": 0.39797234535217285, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/98cf12ee5b532dae0840fa6257ed436112b74189678abf9bad55f2db32e07df9.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "98f6650396c86bbeab55e728aa42c6c2a0effbe071a3d5212d20398fefe723ab", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4b85fbd97195f6ec66d47a0dff8d43a122808ca622706236c411ccb48081d79c", "generation_seconds_batch": 16.168944587931037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5445871949195862, "target_z": 0.12890625259255376, "ce": 6.1020402908325195, "genuineness": 4.105680465698242, "identity": 0.7745492458343506, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/98f6650396c86bbeab55e728aa42c6c2a0effbe071a3d5212d20398fefe723ab.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91ddf796e5fc6a658935b9f1f40175f25807198c4459df90ea7e6f459ad6fa1c", "generation_seconds_batch": 17.122808127081953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16992172598838806, "target_z": -0.3925781366664919, "ce": 6.3641486167907715, "genuineness": 4.607763767242432, "identity": 0.342409610748291, "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_Elation/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "99f61fc173465631d00cc0fe17c3b15a94c21490ceec138a9b391757b510c1cf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dc5983bbe221143d70e9326847c74e9f92bf12aa26cc866249adb08acd263419", "generation_seconds_batch": 25.005733322002925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32147181034088135, "target_z": -0.18164062111116938, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.5390434265136719, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/99f61fc173465631d00cc0fe17c3b15a94c21490ceec138a9b391757b510c1cf.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "9a86bff2fe05147cd6e0b77af25bc187792633231f91438e5e3726791af3a3ff", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b52c085037d2006f199b0aa1076bbaff192875955ebc70f208d5582a5c305a2f", "generation_seconds_batch": 22.738897978910245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4286292791366577, "target_z": 1.359374989629785, "ce": 6.340320587158203, "genuineness": 4.231201171875, "identity": 0.3780425190925598, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9a86bff2fe05147cd6e0b77af25bc187792633231f91438e5e3726791af3a3ff.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "9a9603275d13ef89752142d02a3c39b626e86ca0ddf38513e3c1614439f5a3cf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6a3166423131e159f8c030fd301f1db4cf451138ad5f5b7d7035f294e94b81f8", "generation_seconds_batch": 25.189624635968357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4565337896347046, "target_z": 0.006347650092684834, "ce": 6.078212261199951, "genuineness": 3.9801597595214844, "identity": 0.47453799843788147, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9a9603275d13ef89752142d02a3c39b626e86ca0ddf38513e3c1614439f5a3cf.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "9ae2e3f7d548062ac470655c598aac9d23831868500f780b5f66ce6aa6dde06d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e8e339f8750a2c001b3d0ec9acdc9ef0ffbc4d7a662877f98149cc636ddb1c3b", "generation_seconds_batch": 21.856287656002678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4286292791366577, "target_z": 1.359374989629785, "ce": 6.0305562019348145, "genuineness": 4.337893962860107, "identity": 0.7197493314743042, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9ae2e3f7d548062ac470655c598aac9d23831868500f780b5f66ce6aa6dde06d.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": "9b17e333a7ba57e9a112aafd054d891fce015cc367d335301f892e24eebe4ded", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eae8a69900c1dd5a0449c285cfd085053eb284f8a60b31975cae0cb74c8710ec", "generation_seconds_batch": 23.599875299958512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4596910774707794, "target_z": 0.01074217388909279, "ce": 5.748591423034668, "genuineness": 3.7667744159698486, "identity": 0.23793327808380127, "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_Elation/9b17e333a7ba57e9a112aafd054d891fce015cc367d335301f892e24eebe4ded.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "9b3a594698c5372948b8c665619afb7284ddaed0c8e217192206527a5e0669ee", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "80ee9e624cad6022be64a883d184b39516150439edfc81455755f09c01eba2cc", "generation_seconds_batch": 21.453713039983995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.370715379714966, "target_z": 4.06249995851914, "ce": 5.160833835601807, "genuineness": 3.616149425506592, "identity": 0.5532417297363281, "hypothesis": "¡La puerta sigue abierta! ¡He dejado tu abrigo sobre la silla! ¡Dime cuándo estás listo!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9b3a594698c5372948b8c665619afb7284ddaed0c8e217192206527a5e0669ee.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "9bb4e9a4925bd320e1ad503401a859e5ca8652ecc0f1ff6ba6da33df14002a53", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "49fa0ce8e9018e34606ddfd85050e3c1403c679c9c2f5bb784db88788fa0ff3e", "generation_seconds_batch": 22.421434079064056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.383725643157959, "target_z": 1.296875114072365, "ce": 5.9431867599487305, "genuineness": 4.231201171875, "identity": 0.5282004475593567, "hypothesis": "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_Elation/9bb4e9a4925bd320e1ad503401a859e5ca8652ecc0f1ff6ba6da33df14002a53.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "9bb9119c609313c58e788d1ce33675d0d81e31b67b6664857c0d1e4342d15a4e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "351460abf68962b4a476472d21ab7bcbb04b5ffcecf3f8c85548cb3228c8c8f2", "generation_seconds_batch": 21.023585665039718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4726407527923584, "target_z": 2.8124997925956996, "ce": 6.109982967376709, "genuineness": 3.8169827461242676, "identity": 0.5590481758117676, "hypothesis": "I found a little box. It was beside the old window. We can look inside together", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9bb9119c609313c58e788d1ce33675d0d81e31b67b6664857c0d1e4342d15a4e.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "9bd77bc52244cae6f4e4d07fae6561dd975f7247debd349920380e480d911648", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "89d785c6fce20b13d79e5724a1018497aa91c1e6695fe16a09afed45dcde24b8", "generation_seconds_batch": 16.917030345997773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1021852493286133, "target_z": 2.2968751140723653, "ce": 6.268836498260498, "genuineness": 3.8420867919921875, "identity": 0.31173205375671387, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschachteln.", "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_Elation/9bd77bc52244cae6f4e4d07fae6561dd975f7247debd349920380e480d911648.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "9be39612ef88509a129f54a605a4f53b04ac0f21185ff3da3f1dceb0c2d033bb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "527564aaedf4442babf8b4bd247daa1300522c301d2adca63314005ccc58d021", "generation_seconds_batch": 22.57544781593606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3444347381591797, "target_z": 1.2421874118531724, "ce": 6.165581703186035, "genuineness": 4.432034492492676, "identity": 0.6918457746505737, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9be39612ef88509a129f54a605a4f53b04ac0f21185ff3da3f1dceb0c2d033bb.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "9be54000c606cd625c32e7b6b6bc0dbef6ffdf3bd3f0674f15c81de649654a6c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d538de435585f7890b2abee62853f04d219a14fd4ad090365d4ee5e7e1f4d392", "generation_seconds_batch": 18.371356523013674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4888083338737488, "target_z": 0.05126951342619294, "ce": 6.006728172302246, "genuineness": 3.5094566345214844, "identity": 0.5402761101722717, "hypothesis": "The 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_Elation/9be54000c606cd625c32e7b6b6bc0dbef6ffdf3bd3f0674f15c81de649654a6c.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "9bf76992bb07602c6a1db8e5074aff1f128f9281212aff6ce71d3134cc5e26a9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "acc9042693e9e4c1f58ea6dac9d285027ebdd8cd97f928f21c75cca3c488fee4", "generation_seconds_batch": 23.42483916610945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7036645412445068, "target_z": 1.7421874118531724, "ce": 6.38797664642334, "genuineness": 3.8797430992126465, "identity": 0.4471376836299896, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9bf76992bb07602c6a1db8e5074aff1f128f9281212aff6ce71d3134cc5e26a9.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "2f8287e56e2b04756ee1b48542f609b136ac7d89c300883f2bb85102f6c56481", "generation_seconds_batch": 18.258536695037037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16571199893951416, "target_z": -0.39843751555532253, "ce": 6.2767791748046875, "genuineness": 4.482243061065674, "identity": 0.5996723175048828, "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_Elation/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "9c0e6d06aaf92991b1cf8e7a1f5f1fe848c6f65f7731a4abbd8a3d00cc088dea", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2cb0de52f97eb967f92f4542e4d670e13697183165a299ade602862a158c1b10", "generation_seconds_batch": 22.86453713302035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.052560567855835, "target_z": 0.8359374740744625, "ce": 5.700935363769531, "genuineness": 3.565941095352173, "identity": 0.5598307251930237, "hypothesis": "The 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_Elation/9c0e6d06aaf92991b1cf8e7a1f5f1fe848c6f65f7731a4abbd8a3d00cc088dea.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": "9c1893d10505e3b518f0c1baa50311268eb9a3599b7f25c4fd5c681137334f85", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Your message arrived after I had left.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c45a55c21ccc50a182832616f6daf1f86f2ff60e5f2121c4734c881d12b1cf4", "generation_seconds_batch": 23.373896717093885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6273784637451172, "target_z": 0.24414066259202943, "ce": 6.340320587158203, "genuineness": 4.2249250411987305, "identity": 0.34259697794914246, "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_Elation/9c1893d10505e3b518f0c1baa50311268eb9a3599b7f25c4fd5c681137334f85.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "9c3ccaa267440f09a70581155a0255671fa9b7c8f62eb82368698071816a69eb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b9cf958d665956577720d9c33ca3a7501c9bc3a77a9adc15733e2ff1d6f93647", "generation_seconds_batch": 22.54204666498117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1816587448120117, "target_z": 1.015624927408495, "ce": 5.677107334136963, "genuineness": 3.653805732727051, "identity": 0.20727592706680298, "hypothesis": "De deur 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_Elation/9c3ccaa267440f09a70581155a0255671fa9b7c8f62eb82368698071816a69eb.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e49836465853898b8844dc62cacb61b432be81c0ae6386da6be12e39f5781be1", "generation_seconds_batch": 18.548167441040277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1348406970500946, "target_z": -0.4414062525925537, "ce": 6.205295085906982, "genuineness": 4.595211505889893, "identity": 0.6373863220214844, "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_Elation/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "9d0ae3fcdad0391f5e59210460fdd5c29579ca07cdb2a001713a55ac744cdcca", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f041f0690bb57016a6ffa30f5ad1c0e269f541ef560867a50e4b251722f30dfa", "generation_seconds_batch": 24.305614458979107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4624975621700287, "target_z": 0.014648426481646545, "ce": 6.197352409362793, "genuineness": 3.8295347690582275, "identity": 0.3397414982318878, "hypothesis": "The 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_Elation/9d0ae3fcdad0391f5e59210460fdd5c29579ca07cdb2a001713a55ac744cdcca.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": "9e4ce0672f0b15db168ec6e8e5c9a0f2916ac93ad74e87cd3b124f1ee9621900", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4a409a53c7d9679a7c6abecf13ccab6eb8aded184cb9449bc6e22373a36f8b77", "generation_seconds_batch": 21.895723121007904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8869780898094177, "target_z": 0.6054687370372313, "ce": 6.268836498260498, "genuineness": 4.124508857727051, "identity": 0.5668253898620605, "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_Elation/9e4ce0672f0b15db168ec6e8e5c9a0f2916ac93ad74e87cd3b124f1ee9621900.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": "9eee2520e54946cef8ce55a1b39d0be3180651d790a09aaf92895eb2013205e0", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Escribí el número en el sobre.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da1e2541c5236670aa38b41c9d1e7f7d6aeea557e9a604395513fbc33799ab7b", "generation_seconds_batch": 21.176260918029584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6306960582733154, "target_z": 1.640625010370215, "ce": 6.125868320465088, "genuineness": 4.105680465698242, "identity": 0.6549631953239441, "hypothesis": "Escribí el número en el sobre, léérelo 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_Elation/9eee2520e54946cef8ce55a1b39d0be3180651d790a09aaf92895eb2013205e0.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "9fb5a8acb214520c2c60c56a710786b99bec8a5ad40c84748b05be0b06c9c4e3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1b5a2efd6eaedeb457774e268ba08b8ca11e99d97071d107738acbb473a4663b", "generation_seconds_batch": 24.512202923069708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5801794528961182, "target_z": 1.5703126296276877, "ce": 6.165581703186035, "genuineness": 4.287685871124268, "identity": 0.24507857859134674, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/9fb5a8acb214520c2c60c56a710786b99bec8a5ad40c84748b05be0b06c9c4e3.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "9fd2e89573ca8013aec218849e3b10b3dc929a79f0045e819f87922ac78728c5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f59e6be2762483020b4bd3cadeff945d931be16a20994cbcffa69ab2d4ac3d08", "generation_seconds_batch": 22.635196528979577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.584900140762329, "target_z": 2.96874989629785, "ce": 6.062326908111572, "genuineness": 4.2249250411987305, "identity": 0.5713093280792236, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay detrás.", "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_Elation/9fd2e89573ca8013aec218849e3b10b3dc929a79f0045e819f87922ac78728c5.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "9ffa74d5d19d66e5e46a88bf8ea35b7978ba6c4d05503223ce9fdce5f941d36c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ddcdac65764f125c77a957a958b5441773b2a3e017e3a5c98cb8cd04e1bcd2c5", "generation_seconds_batch": 21.300581544986926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12080827355384827, "target_z": -0.46093751555532253, "ce": 6.1020402908325195, "genuineness": 4.325342178344727, "identity": 0.6459197402000427, "hypothesis": "La porte 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_Elation/9ffa74d5d19d66e5e46a88bf8ea35b7978ba6c4d05503223ce9fdce5f941d36c.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "a0075af34e07e15d1cbc363a8fa7a99c4e0fefc00727131a58c7382647746db8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "99b33009ca48d1e3c9f219e87ab23e3b9418f2a5521e9e0fa357fca11fdc8093", "generation_seconds_batch": 17.09765798598528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5240497589111328, "target_z": 1.4921875777766127, "ce": 6.332377910614014, "genuineness": 4.419482707977295, "identity": 0.3577767014503479, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a0075af34e07e15d1cbc363a8fa7a99c4e0fefc00727131a58c7382647746db8.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "a020bd3ee970e9c4400d38b9ab79d8ae9717837c084e2875d7add1716054bc0f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7c9344b090e554b25266167db52dc5eba4574731014e1e0a6684daf737382b7a", "generation_seconds_batch": 22.040336080943234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4021582007408142, "target_z": -0.06933592129653904, "ce": 6.1894097328186035, "genuineness": 4.218649387359619, "identity": 0.762923002243042, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a020bd3ee970e9c4400d38b9ab79d8ae9717837c084e2875d7add1716054bc0f.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "a03e4521fe9d4c42e1a550c85edb94fdc0f7a22f5fedeb1dc35674bcecbfec02", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7d6a580e06bdfdccd7cb89a72af3a812225855944c9547ba2b6e183be92d54ac", "generation_seconds_batch": 16.604435968096368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.899226188659668, "target_z": 3.40624985481699, "ce": 5.700935363769531, "genuineness": 3.8044304847717285, "identity": 0.3257071375846863, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a03e4521fe9d4c42e1a550c85edb94fdc0f7a22f5fedeb1dc35674bcecbfec02.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "a04f8eb9561918fbb116d826ae941de02d045e0405c6528cdec41ec9cd9c43f4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "006599fa4568d6c4bdbd1daacc8c3347c6e48755ea4d470eaaf1871541367b07", "generation_seconds_batch": 22.108214321080595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2818000316619873, "target_z": 2.546874948148925, "ce": 5.414999485015869, "genuineness": 3.5565271377563477, "identity": 0.45460376143455505, "hypothesis": "De deur 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_Elation/a04f8eb9561918fbb116d826ae941de02d045e0405c6528cdec41ec9cd9c43f4.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": "a06b3e855448078f6267ef55e2411c643eb05a5d1615a457e08d8235a7cafeaf", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "276623be813e228fbd10b4a78984162efb06a94ccad9b1cb6a564055e61ee333", "generation_seconds_batch": 21.895723121007904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.714890480041504, "target_z": 1.7578124222233873, "ce": 6.086154937744141, "genuineness": 4.394378662109375, "identity": 0.7982193827629089, "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_Elation/a06b3e855448078f6267ef55e2411c643eb05a5d1615a457e08d8235a7cafeaf.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "a0d1cc7a16c520f3b88e22f264f52471544184ef76a4cfcecbdfea7b7ac5d720", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "442d23487a53806b80935eb5707d0fc263c339819e294b3ec65870d763d94dcc", "generation_seconds_batch": 23.6200145840412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9346883296966553, "target_z": 0.6718750311106451, "ce": 5.847874641418457, "genuineness": 3.9801597595214844, "identity": 0.6476303339004517, "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_Elation/a0d1cc7a16c520f3b88e22f264f52471544184ef76a4cfcecbdfea7b7ac5d720.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "a1090f45c38981ccc5a11325aaf565ee76813b314bbf69957e1c60980ba01ad6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c351da8beb5efc25b56955a0b0681fcea28c30fb0ad1c5e7893eca06b1681082", "generation_seconds_batch": 22.930367987952195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8504937887191772, "target_z": 0.5546874533340325, "ce": 5.71682071685791, "genuineness": 4.124508857727051, "identity": 0.44851022958755493, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a1090f45c38981ccc5a11325aaf565ee76813b314bbf69957e1c60980ba01ad6.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "a120737615063ec24e3e34098c77acb99af56852de83e78b35e77d34fef5cd2d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0abdfd3f6ec52f16e70a5f070d6dbcb1edee14527bfea0e335c488e6740815b7", "generation_seconds_batch": 14.945116931921802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6082441806793213, "target_z": 1.609374989629785, "ce": 6.062326908111572, "genuineness": 4.055472373962402, "identity": 0.3556201159954071, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a120737615063ec24e3e34098c77acb99af56852de83e78b35e77d34fef5cd2d.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "a18b1549b68718990a72088b49093845862df2138a3b57d2b4863c991a727f7b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c289413690370aae255266a09150bada5cecba71a378493bc0054fdee9b1fd0f", "generation_seconds_batch": 22.697545998031273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.079733371734619, "target_z": 2.265625093331935, "ce": 5.6413655281066895, "genuineness": 3.911123275756836, "identity": 0.5927256345748901, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a18b1549b68718990a72088b49093845862df2138a3b57d2b4863c991a727f7b.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": "a1e899b2083ac3e59c664ba20b877976b7ca7b34a261dbc8f8172b2b32b9be1a", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bec1e6e03bb548c6110c219f4cbb8a1fcd7ecc6bfeb706b44021dc1f4d8bc258", "generation_seconds_batch": 16.7114627660485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1713249683380127, "target_z": -0.390625010370215, "ce": 6.070269584655762, "genuineness": 3.8295347690582275, "identity": 0.6881431341171265, "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_Elation/a1e899b2083ac3e59c664ba20b877976b7ca7b34a261dbc8f8172b2b32b9be1a.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "a2110590375a51d143db9ae96f945c99821173ef8aa06497045fc090000f270c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3413d38c326843726f50cfb77c66ad4d9c500f16ed276e2b7e4b1336b4aca7f8", "generation_seconds_batch": 23.25605090300087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2602403163909912, "target_z": 1.125, "ce": 6.038498878479004, "genuineness": 4.118232727050781, "identity": 0.36108025908470154, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a2110590375a51d143db9ae96f945c99821173ef8aa06497045fc090000f270c.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": "a219e435193d8c6359c01c556e4c9603587b791666d2432eee1a789ff7801548", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3224ab7d0c47c4555e4bc1f6f6977c659a3b0fa3b33aedd37991d825aab83089", "generation_seconds_batch": 20.84394112508744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0946578979492188, "target_z": 0.8945313459244889, "ce": 6.229123115539551, "genuineness": 4.18099308013916, "identity": 0.4554884135723114, "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_Elation/a219e435193d8c6359c01c556e4c9603587b791666d2432eee1a789ff7801548.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "a22851fa97fe9bc28ac3e0ac18b1c8b7069c74090ee7c79e238e4f41845a9797", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0b43eada8870aa812770f421a55c2e5bcc9888c865992455d2f63e56feba442f", "generation_seconds_batch": 22.545745374984108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1470890045166016, "target_z": 2.3593751555532254, "ce": 6.133810997009277, "genuineness": 4.356721878051758, "identity": 0.6726590394973755, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a22851fa97fe9bc28ac3e0ac18b1c8b7069c74090ee7c79e238e4f41845a9797.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "a25e33f192aafc25280148fb4cf45ed163b471f47461c4e7aba4548adc0cb089", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2bf8e791d81ded5bef4e764e3a44c7f270faa82b9bc6d8c81f54795fd822bd3b", "generation_seconds_batch": 17.78173051297199, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2930259704589844, "target_z": 2.56249995851914, "ce": 5.704906940460205, "genuineness": 3.747946262359619, "identity": 0.5223055481910706, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a25e33f192aafc25280148fb4cf45ed163b471f47461c4e7aba4548adc0cb089.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "a260309cd7bdf0e6ac660069ede5c816bbdd37610041933c92ad7b8efbfb9d72", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2b394741ca7fccc81454cc8ceadf82956ed4466215a8e6d47e7a79bdddabac62", "generation_seconds_batch": 23.267392192035913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7312183380126953, "target_z": 0.3886719255547982, "ce": 6.41180419921875, "genuineness": 4.15588903427124, "identity": 0.4924475848674774, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a260309cd7bdf0e6ac660069ede5c816bbdd37610041933c92ad7b8efbfb9d72.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "a2b3c8f2984168be44a6214170f37f95542d86d267e083ead360aaa6766f417a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "505be7636e43fe85c1997dcf9e596527bdaf11b666efee8e25fdc096985fc246", "generation_seconds_batch": 24.19358698592987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5970182418823242, "target_z": 1.59374997925957, "ce": 6.157639026641846, "genuineness": 4.093128204345703, "identity": 0.388062059879303, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a2b3c8f2984168be44a6214170f37f95542d86d267e083ead360aaa6766f417a.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": "a30902eebcb43c4705c85c0dae496f9732f341696a1bb21645ce7723f16f7030", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1904492a7d48ea5a8edce532729f6cc6ff5ce72174877afbb48414fc412d75f8", "generation_seconds_batch": 15.24906518298667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8925910592079163, "target_z": 0.6132812422223387, "ce": 6.205295085906982, "genuineness": 4.256305694580078, "identity": 0.7548538446426392, "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_Elation/a30902eebcb43c4705c85c0dae496f9732f341696a1bb21645ce7723f16f7030.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "a388062495b6410f4e802dd3d653fffbc84375dc7d6f24255174146e0baeb91f", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1fa7f30c5184d8ad52e5d21936baf6a70f08183b0e2be8e4671081022a9fd431", "generation_seconds_batch": 18.547662094933912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1306309700012207, "target_z": -0.4472656314813844, "ce": 6.133810997009277, "genuineness": 3.5847692489624023, "identity": 0.44951480627059937, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a388062495b6410f4e802dd3d653fffbc84375dc7d6f24255174146e0baeb91f.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "a3c16cf69ec962815ff62e3aa826b6106f62ce07b9739ed516eefab9a98b0943", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f10fd7e484553ef78d1a2bf4230d36c56e1f2f27b1e3a0954fe89ea64436ad04", "generation_seconds_batch": 17.33078374399338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6980516910552979, "target_z": 1.734375072591505, "ce": 5.760505676269531, "genuineness": 3.6914620399475098, "identity": 0.3979966640472412, "hypothesis": "The 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_Elation/a3c16cf69ec962815ff62e3aa826b6106f62ce07b9739ed516eefab9a98b0943.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "a46383c7512f6d66d9f314aafa79f219f14144b4a7506f230d700a705aa974e0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1237e9a9db125c9809880b2f1c471223b97a42f9149d68b29ed21cd2f75b76fc", "generation_seconds_batch": 23.265388414962217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1367549896240234, "target_z": 0.9531248859276348, "ce": 5.704906940460205, "genuineness": 3.747946262359619, "identity": 0.5954663157463074, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a46383c7512f6d66d9f314aafa79f219f14144b4a7506f230d700a705aa974e0.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": "a4bc4e9488146a8cd75ed59a28020bddf5ec5cfda368c444d90ced0455a0ddd2", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39fc3c3cbf2bc8d1d9540956031684dd077716d74b515b2b05238755a1ad9a96", "generation_seconds_batch": 21.13838299701456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38251280784606934, "target_z": -0.09667968944441531, "ce": 6.221180438995361, "genuineness": 3.8295347690582275, "identity": 0.6069138050079346, "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_Elation/a4bc4e9488146a8cd75ed59a28020bddf5ec5cfda368c444d90ced0455a0ddd2.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "a4f20fa5806616f4499deb74348c291e0aff5fd219578bce212234d8a6086828", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fdee5cc075a8ddf8a3feb0b6b60b914848201f6a621bc10e023c09c328870d24", "generation_seconds_batch": 16.92369428393431, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2826921939849854, "target_z": 1.15625002074043, "ce": 6.41180419921875, "genuineness": 3.936227321624756, "identity": 0.16898402571678162, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a4f20fa5806616f4499deb74348c291e0aff5fd219578bce212234d8a6086828.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "a51f378ad1191223d893aaab3327a839a64d2b7742e9140a2cf5411798ad0dc9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a7b724118fe5c9aea44ce65d9f5f45994a176e586683d79225fc7c396515e14a", "generation_seconds_batch": 26.66514426690992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2814794182777405, "target_z": -0.23730469981463034, "ce": 6.23706579208374, "genuineness": 3.986435890197754, "identity": 0.3117722272872925, "hypothesis": "The 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_Elation/a51f378ad1191223d893aaab3327a839a64d2b7742e9140a2cf5411798ad0dc9.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "a5d71f374f429557cd4ae29f08cb318be3425a1ce75663b5e6df231102ba1e79", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d862eddddabd825bcf3497563499f4c432472123611e2e1b2b3b196dff2b95d7", "generation_seconds_batch": 21.68981385801453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.090959310531616, "target_z": 2.28125010370215, "ce": 6.213237762451172, "genuineness": 3.936227321624756, "identity": 0.6821885108947754, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a5d71f374f429557cd4ae29f08cb318be3425a1ce75663b5e6df231102ba1e79.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "a5d8a5ade4e0cb0a36a46f01796d0b7dcb79ece763c3f8f7055ab029042c0035", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4adce2281201f2230a4813c8cdb42c00eb4ac528e54b4680327764bf63ba05c8", "generation_seconds_batch": 24.305614458979107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13764718174934387, "target_z": -0.4375, "ce": 6.062326908111572, "genuineness": 3.613011360168457, "identity": 0.24678713083267212, "hypothesis": "The 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_Elation/a5d8a5ade4e0cb0a36a46f01796d0b7dcb79ece763c3f8f7055ab029042c0035.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "a662504ed57d1c9f77d105f1904ff72f6313a5bc4f35910beddf7761992edf62", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "878f7c227767dd373e08c5b80725aecd013bc551c4896045118706a90b33f176", "generation_seconds_batch": 23.270001942990348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39023062586784363, "target_z": -0.08593751555532253, "ce": 6.324435234069824, "genuineness": 4.319066047668457, "identity": 0.4240630865097046, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a662504ed57d1c9f77d105f1904ff72f6313a5bc4f35910beddf7761992edf62.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "a75b969f112af91d6d586655e79f2302b656e0f1c3986b77efd11acf5626ed78", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dcdc8340ac3dd2b2cd673d5ff70da54d23e430b913c35d5b531ede750707c4f6", "generation_seconds_batch": 25.382392905070446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7340247631072998, "target_z": 0.3925780951856318, "ce": 5.788304805755615, "genuineness": 3.735394239425659, "identity": 0.4141116142272949, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a75b969f112af91d6d586655e79f2302b656e0f1c3986b77efd11acf5626ed78.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "a75df449b14b83010db791cbb04184c7371826be98729550d109821cc49c6d37", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "14c6290f86fa79c869c34358288316cdc869ae8b0d436d2e19a43dfdd408ee14", "generation_seconds_batch": 21.23753822792787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5408885478973389, "target_z": 1.515624927408495, "ce": 6.356205940246582, "genuineness": 3.9299514293670654, "identity": 0.5403485298156738, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinstehen.", "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_Elation/a75df449b14b83010db791cbb04184c7371826be98729550d109821cc49c6d37.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "a765ac7260ec7081c9ed0de3c017098c214d7a84392dfc93179c670060d8048c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5a9af53f475f8bbde5bcbecfe248847d18d98d0adf3c1dc060213fdfccf8824", "generation_seconds_batch": 23.08792493492365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6807016134262085, "target_z": 0.31835937888883065, "ce": 6.149696350097656, "genuineness": 4.168440818786621, "identity": 0.5353944301605225, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a765ac7260ec7081c9ed0de3c017098c214d7a84392dfc93179c670060d8048c.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "a7b197dad24d61421f1ac29a7c4bf66433bdd7ef56798934f55f4d876af19865", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "62c616ebc98212bedb59671f1a5aaa593e9edfcddde97855ab870312090d2366", "generation_seconds_batch": 23.57547669392079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6747076511383057, "target_z": 3.09374997925957, "ce": 6.086154937744141, "genuineness": 4.099404335021973, "identity": 0.6205430030822754, "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_Elation/a7b197dad24d61421f1ac29a7c4bf66433bdd7ef56798934f55f4d876af19865.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "c5c5599f1a91d89e4c2bb24a57297aec8ce70c3ce51746404f3dd3dbac92974c", "generation_seconds_batch": 18.263021891005337, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08151751756668091, "target_z": -0.515625010370215, "ce": 6.1020402908325195, "genuineness": 4.105680465698242, "identity": 0.6255866289138794, "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_Elation/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea", "bucket": "emo_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "cd20bf53d076174d83a829a34adee096c8399f5f93e3875023aa9b04a2f68d84", "generation_seconds_batch": 16.906058504944667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17272821068763733, "target_z": -0.38867188407393816, "ce": 6.197352409362793, "genuineness": 4.557555198669434, "identity": 0.6917355060577393, "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_Elation/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "a97eedde6b893c8867638a00695b4cb98895f49b30838c8049435817a20c625b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8694ad29b487c5f8e9601592d38cab9534b1be30921e5124d12a20fb6e29aec5", "generation_seconds_batch": 17.831443522009067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4174033403396606, "target_z": 1.34374997925957, "ce": 6.133810997009277, "genuineness": 3.848362922668457, "identity": 0.5451602935791016, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/a97eedde6b893c8867638a00695b4cb98895f49b30838c8049435817a20c625b.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": "aa2bcc98cf60a1aa07a291994a3fc239b5d7ba7fdc688f913b1f6259bc047a44", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d35c77ae8666304eb6dfbc6acd837b2d547749478426e56afa3e42af2f9be615", "generation_seconds_batch": 21.719308647094294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6298038959503174, "target_z": 3.03124993777871, "ce": 6.038498878479004, "genuineness": 4.086852550506592, "identity": 0.08650583773851395, "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_Elation/aa2bcc98cf60a1aa07a291994a3fc239b5d7ba7fdc688f913b1f6259bc047a44.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "aaff5b50a5b743613d8dfb3003bfc88663096ba63e8f19578051bb13dca7a818", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "111031888e04593b34e7aa3e98c0b2e986d1e00e27f66ab89d4eba4680cd45e1", "generation_seconds_batch": 22.141028495971113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1349709033966064, "target_z": 3.7343750725915053, "ce": 5.748591423034668, "genuineness": 3.9425034523010254, "identity": 0.4602060914039612, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/aaff5b50a5b743613d8dfb3003bfc88663096ba63e8f19578051bb13dca7a818.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": "ab15e8d01e9fb8af56ee5068337f65e08039a0bf3be1be1a87f52205aa028841", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "beb76be50bbadbb7c32e13c2ce0420149c03d4cb203e647dcd4099cb3eda4031", "generation_seconds_batch": 19.62183290894609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5873860716819763, "target_z": 0.18847658388856847, "ce": 6.165581703186035, "genuineness": 4.218649387359619, "identity": 0.7736701965332031, "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_Elation/ab15e8d01e9fb8af56ee5068337f65e08039a0bf3be1be1a87f52205aa028841.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "ab324540a134dbfabc541efd5dd7c4744e3dbd34ec7da2f0e89a6f052c3666c0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c096cdd32304d83f3fdaa41e5c3d72fa1440250b9b622c7400e8eb3ab09b1420", "generation_seconds_batch": 22.702530851005577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6764918565750122, "target_z": 0.3124999585191399, "ce": 6.316492557525635, "genuineness": 4.375550270080566, "identity": 0.6708407402038574, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ab324540a134dbfabc541efd5dd7c4744e3dbd34ec7da2f0e89a6f052c3666c0.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": "ab752ea2d7f4446f2fb0f2ae1c963574347675967cacbb891b1cf8feec79862d", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fa754cab05ff23104568f4220687207eaeec2517edab7c2878ee1070994fcd5", "generation_seconds_batch": 17.796131195966154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16992172598838806, "target_z": -0.3925781366664919, "ce": 6.09409761428833, "genuineness": 4.68307638168335, "identity": 0.8301595449447632, "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je 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_Elation/ab752ea2d7f4446f2fb0f2ae1c963574347675967cacbb891b1cf8feec79862d.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "edb6d98ebd0c0d8afb8806099382fd4991aa658544def4daa39e656622588293", "generation_seconds_batch": 17.01676122599747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08432400226593018, "target_z": -0.5117187577776613, "ce": 6.467403411865234, "genuineness": 4.293961524963379, "identity": 0.3807058334350586, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "aba125b521caf688d7c730d04051161d85a22430880c099ceea04c8b4c8c2ce5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "241bf39e852c60c6be4ab6afb0b1df2e298a04d78420ecb4665b1fb5d6776601", "generation_seconds_batch": 23.946009433013387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9262688159942627, "target_z": 0.6601561903712636, "ce": 6.2767791748046875, "genuineness": 4.218649387359619, "identity": 0.26375633478164673, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/aba125b521caf688d7c730d04051161d85a22430880c099ceea04c8b4c8c2ce5.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": "abc320a3db73c5c14428c9dd7b7c0caaa0d19747a618e6518ec416c7fb9f3e20", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Escribí el número en el sobre.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3863e0857460b7b75fe2a08627d1dcfb07d0730fe2bf39e70d65e0a903eb5776", "generation_seconds_batch": 21.02334258297924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2770792245864868, "target_z": 1.1484375155553226, "ce": 6.205295085906982, "genuineness": 4.086852550506592, "identity": 0.6136111617088318, "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_Elation/abc320a3db73c5c14428c9dd7b7c0caaa0d19747a618e6518ec416c7fb9f3e20.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "ac1b5399d44ea8d57e314e5c7e618b9a62f0d9471dec09dd50242ae54fbc0f14", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0bcfda48fd60114213d4a18e51c3b01b6b0e5f7c3f7bb32014eff6c331ea614f", "generation_seconds_batch": 22.307883083005436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3853192925453186, "target_z": -0.09277343685186157, "ce": 6.252951145172119, "genuineness": 4.168440818786621, "identity": 0.738106369972229, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ac1b5399d44ea8d57e314e5c7e618b9a62f0d9471dec09dd50242ae54fbc0f14.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "ac8a350ecadc21fc1efb8a7a7932b581ad08240b61f6b99d1e9b8f4655043ebd", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9c4c56c5baaecb5bc7ff52230dd9aa28517735b9f6b6fd6ab0dff687ed3ba48d", "generation_seconds_batch": 24.38813776895404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.360381603240967, "target_z": 2.65625002074043, "ce": 5.998785495758057, "genuineness": 3.735394239425659, "identity": 0.3536478877067566, "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_Elation/ac8a350ecadc21fc1efb8a7a7932b581ad08240b61f6b99d1e9b8f4655043ebd.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "acd17e8ab4233a94e86a678b40d430927e780f9b4db5913fc36f202f01792301", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69d5fb49854c00dc570a03f0b7a79f36d5b9cd903c798c9ebd1615820ff52a00", "generation_seconds_batch": 24.14089886203874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3154778480529785, "target_z": 2.59374997925957, "ce": 5.871703147888184, "genuineness": 4.080576419830322, "identity": 0.5639523267745972, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/acd17e8ab4233a94e86a678b40d430927e780f9b4db5913fc36f202f01792301.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "acf9aec981b54b2c4c91c612f2d54412de1690e2e38d5d49bb342756b8a5cb2a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e1d549779452500267de07e33c330c592b2ec422a347628617425dfea1220865", "generation_seconds_batch": 22.702530851005577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7733155488967896, "target_z": 0.4472656314813844, "ce": 6.078212261199951, "genuineness": 4.017816066741943, "identity": 0.6496745347976685, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/acf9aec981b54b2c4c91c612f2d54412de1690e2e38d5d49bb342756b8a5cb2a.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "ad068ab775d94cefb04122db0f375003f6665b6ea30181230361417216667e3a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "02bc41288f3b568ff4705362b168f9dca02c04c032339fb8a2f21e667087d08d", "generation_seconds_batch": 22.75308428599965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4838666915893555, "target_z": 2.8281248029659145, "ce": 6.197352409362793, "genuineness": 3.860914945602417, "identity": 0.3569079637527466, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.", "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_Elation/ad068ab775d94cefb04122db0f375003f6665b6ea30181230361417216667e3a.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "ad2bb49539917dd4972c8fcf9d6c3aaa760619addec273bb1af3bc5a2b1390cd", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "956457acbd6425972abf7e2932dea9df59057ff91002a1f04c442690f8eacb04", "generation_seconds_batch": 22.318446271005087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5015978813171387, "target_z": 1.4609375570361827, "ce": 6.316492557525635, "genuineness": 4.362998008728027, "identity": 0.27134469151496887, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ad2bb49539917dd4972c8fcf9d6c3aaa760619addec273bb1af3bc5a2b1390cd.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "ad4806e16417f2415b5ad2819e9fdedac477b822d82050e2c86fe8151b56817c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e942830b006443c03fdeeaf474bc1769276555f7a9b15c53f5038e095cdf38ad", "generation_seconds_batch": 25.505774015909992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3612737655639648, "target_z": 1.265625093331935, "ce": 6.284721851348877, "genuineness": 4.532451152801514, "identity": 0.5999441742897034, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ad4806e16417f2415b5ad2819e9fdedac477b822d82050e2c86fe8151b56817c.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "ad5854bd3be89d5c1e1e85f382bf36f4bfd1f15f02e466304c4795ba57ccd7e6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "93d1487307866b8002c35236b6fdce831a8322c108ad67cf88d8293c7f269021", "generation_seconds_batch": 16.576256926055066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5116110444068909, "target_z": 0.08300784685133725, "ce": 6.1894097328186035, "genuineness": 4.20609712600708, "identity": 0.6219825148582458, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ad5854bd3be89d5c1e1e85f382bf36f4bfd1f15f02e466304c4795ba57ccd7e6.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "27d2d22fd726c605413f39c836782c544327ad718eb9635f05e852f8a2a09920", "generation_seconds_batch": 17.04971778905019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22184166312217712, "target_z": -0.3203125051851075, "ce": 6.173524379730225, "genuineness": 4.362998008728027, "identity": 0.7126582860946655, "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_Elation/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "adf6d4a8b1245d083798b25bfcc8f56f0c81b907bd0d9471ea370cadc902cd3a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ece9d41ab69e4b7de18c0769038a03c3bbda189fa684e79382dbd145d587ecdc", "generation_seconds_batch": 22.067212685011327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5782649517059326, "target_z": 0.17578120074147868, "ce": 6.2767791748046875, "genuineness": 3.9550557136535645, "identity": 0.5247156620025635, "hypothesis": "Ik 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_Elation/adf6d4a8b1245d083798b25bfcc8f56f0c81b907bd0d9471ea370cadc902cd3a.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "8879476469d612a30d46334772f53c7be7032516214c90b8498d5f15ca87eb91", "generation_seconds_batch": 17.08410511096008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07871103286743164, "target_z": -0.5195312629627687, "ce": 6.443574905395508, "genuineness": 4.570107460021973, "identity": 0.4396194815635681, "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_Elation/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "ae4427180d5e44c9196f19aad941a25b580c4ce9858f7c7abd74b61f42d08906", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "292bfb6894ab16aaf35f7ec3984ae7553ab81c9fc0b96baa0353ab297e5e530b", "generation_seconds_batch": 23.36523894604761, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.033937454223633, "target_z": 3.59374997925957, "ce": 5.605623245239258, "genuineness": 3.8922953605651855, "identity": 0.5122270584106445, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ae4427180d5e44c9196f19aad941a25b580c4ce9858f7c7abd74b61f42d08906.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "ae97a0a4aaa5b2e9bfeb5a72cacf32cc6c103662768d94c284a7d76b5e7a6d49", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a58e9442f1495cb5231ab03cc556c3df173365b13de7099ec87902c83aca1264", "generation_seconds_batch": 22.193225017981604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4623069763183594, "target_z": 1.4062498548169897, "ce": 6.046441555023193, "genuineness": 3.7793264389038086, "identity": 0.4030226469039917, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ae97a0a4aaa5b2e9bfeb5a72cacf32cc6c103662768d94c284a7d76b5e7a6d49.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "aee6d4aa7dbb21f8983d1de02bcb30c96f463e0d72803aabe63c8a20088a91b1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9e0c0587f931f2ab8d8b6238a8b17b7690deff98be08112afb37a994846e5335", "generation_seconds_batch": 17.232418443076313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8069933652877808, "target_z": 0.49414066259202943, "ce": 5.6254801750183105, "genuineness": 3.565941095352173, "identity": 0.1458541601896286, "hypothesis": "Ik 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_Elation/aee6d4aa7dbb21f8983d1de02bcb30c96f463e0d72803aabe63c8a20088a91b1.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "afbc4e095bf7fc359902b1929ccf06e93c871c439bcbf25da6aa75654078af9f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6cddb271bd66afcca0a66646257aa057c80bb31a4976bc3b719593a86a81a6c3", "generation_seconds_batch": 17.69113864505198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6077330708503723, "target_z": 0.21679689444415315, "ce": 5.919358730316162, "genuineness": 4.1998209953308105, "identity": 0.6500915288925171, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/afbc4e095bf7fc359902b1929ccf06e93c871c439bcbf25da6aa75654078af9f.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "b005f5de3f9e6c8571bab28b05151ae06f23518971b56e6874d3e4de3278e569", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3efe37116a1d066a4d9c9e22d2a8286f223c5c29f97a3fd1077d6ea59b1bcfd", "generation_seconds_batch": 16.704456723993644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.932904005050659, "target_z": 3.4531248859276347, "ce": 6.300607204437256, "genuineness": 3.9299514293670654, "identity": 0.4825136661529541, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b005f5de3f9e6c8571bab28b05151ae06f23518971b56e6874d3e4de3278e569.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "b0d4d1860b020708cdac88aaa14cdfcde0e5c30dba1709a6eecc7c5cba474781", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5e34d8b26572c1718d206154f4dc50645ab7a443777c58a2e5b937126364808a", "generation_seconds_batch": 21.933779336046427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17272821068763733, "target_z": -0.38867188407393816, "ce": 6.284721851348877, "genuineness": 4.457139015197754, "identity": 0.7223113775253296, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b0d4d1860b020708cdac88aaa14cdfcde0e5c30dba1709a6eecc7c5cba474781.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "b0e21e68bf6a2b625cbe8869f769d575e91b0b3497144cf6bce509722dcce194", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e898d0370ad58e9f782016b81b6e0513b343db6ec9f88ea012d164ac5de102ff", "generation_seconds_batch": 23.151798023027368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9290753602981567, "target_z": 0.6640625259255375, "ce": 6.062326908111572, "genuineness": 3.9676074981689453, "identity": 0.5498940944671631, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b0e21e68bf6a2b625cbe8869f769d575e91b0b3497144cf6bce509722dcce194.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "b1021a05a057644cd8fb2509ae855b8a4d14d8baf652cfddb6737ac20de191b0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6e03e4d76e276828ca749b5213cd4ad1e412d6846e3eee784827a1a080a177d9", "generation_seconds_batch": 21.881187623017468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15729257464408875, "target_z": -0.41015623185212374, "ce": 6.109982967376709, "genuineness": 4.193545341491699, "identity": 0.7595944404602051, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b1021a05a057644cd8fb2509ae855b8a4d14d8baf652cfddb6737ac20de191b0.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "b1c23e73f05d1735a4f148fad893bf1b152d527585dfa7977b6cd3198887df63", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2aa874b58430f4db2d281ebd44b9393e811c47c73663156f513efedbe44f3185", "generation_seconds_batch": 21.592055983026512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6747076511383057, "target_z": 3.09374997925957, "ce": 5.982900142669678, "genuineness": 3.923675537109375, "identity": 0.5031337141990662, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b1c23e73f05d1735a4f148fad893bf1b152d527585dfa7977b6cd3198887df63.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": "b2107b8219238ccd9df8ba1153f9ffb67b9ee528cf13fc2a3c1712d986923cfe", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Escribí el número en el sobre.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18ca8d51b439f6e27d3aaaaef7f9eb891f478d9fbc83227f730ac90b9f820044", "generation_seconds_batch": 21.02334258297924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.360381603240967, "target_z": 2.65625002074043, "ce": 6.213237762451172, "genuineness": 4.068024158477783, "identity": 0.514061450958252, "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_Elation/b2107b8219238ccd9df8ba1153f9ffb67b9ee528cf13fc2a3c1712d986923cfe.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "b2c5e5b8335ba3ea635e87cc137c8ee11ad025caa2360051cef2aa50dad52869", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e74d7bc9fef4aa075dce5ed9c6af69c986ec5b4074846565cefce8c0f5c82486", "generation_seconds_batch": 24.44640030199662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9225702285766602, "target_z": 2.046874948148925, "ce": 6.348263263702393, "genuineness": 4.055472373962402, "identity": 0.36709558963775635, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b2c5e5b8335ba3ea635e87cc137c8ee11ad025caa2360051cef2aa50dad52869.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "b310ae3cb066e5ddcf64f548c0ce8e8189e4a7464be7f2a763417f55c90d5bed", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f7808121cc9568a4666e9c3e650d4f0a2f676b29135ddff3525f91a984371cf6", "generation_seconds_batch": 24.58720099402126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8953975439071655, "target_z": 0.6171874948148925, "ce": 6.372091293334961, "genuineness": 4.118232727050781, "identity": 0.3623015284538269, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b310ae3cb066e5ddcf64f548c0ce8e8189e4a7464be7f2a763417f55c90d5bed.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "b3569796efcf1d8a0f5fe95a0d440a09f6a048ac163121a79968473546e7dda2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "62f18bf223eb8c61283253f1ec3bf6e0a2bb37622e6bf94f3b556cb5f60202f1", "generation_seconds_batch": 26.66514426690992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12922772765159607, "target_z": -0.44921875777766124, "ce": 6.2767791748046875, "genuineness": 4.030367851257324, "identity": 0.16766519844532013, "hypothesis": "The 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_Elation/b3569796efcf1d8a0f5fe95a0d440a09f6a048ac163121a79968473546e7dda2.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "cb8531e9bab38ff02dd9dc42ae3ae6d037e0c9800031a843a7dfd8f973f65e95", "generation_seconds_batch": 17.62010373699013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14045366644859314, "target_z": -0.4335937474074463, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.5244677066802979, "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_Elation/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.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": "b4aa7a542be16c1084c4137eb7c007355df794350921caa1eb06bede68421934", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0b1d54275dc3b84d1a68898cd05a32480bf9a8340245a6a9077daa4693625cf8", "generation_seconds_batch": 22.61288313800469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0581735372543335, "target_z": 0.84374997925957, "ce": 6.2767791748046875, "genuineness": 4.218649387359619, "identity": 0.6524934768676758, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayan.", "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_Elation/b4aa7a542be16c1084c4137eb7c007355df794350921caa1eb06bede68421934.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": "b4e89c5eb90f9f4c8fc2c52a0d335b14f615b0fedfe872c4427dd563e527c529", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a35461ff6a74df4199a23f29f005e2309c6cc26150e596f12c9857cfe88a9ae", "generation_seconds_batch": 21.719308647094294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3612737655639648, "target_z": 1.265625093331935, "ce": 6.038498878479004, "genuineness": 4.099404335021973, "identity": 0.4961796998977661, "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_Elation/b4e89c5eb90f9f4c8fc2c52a0d335b14f615b0fedfe872c4427dd563e527c529.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "b5862ca7f52a9f523ae3cb470645f80f009ddea0e99222d39ce5c1b4b48e23d5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "49b8cd71c9ba5c83ddad8b8691e3fc20e950575afb70683ff87c2522e8f41541", "generation_seconds_batch": 17.360641640028916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6531479358673096, "target_z": 1.671875031110645, "ce": 6.324435234069824, "genuineness": 3.911123275756836, "identity": 0.46457812190055847, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b5862ca7f52a9f523ae3cb470645f80f009ddea0e99222d39ce5c1b4b48e23d5.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "b5e0c806fa77b35c3b68b8bb9dd54a1fcc89d235f44b569e4e4c73003c66dafe", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b2e740b02f65e0fc49a70c489335af91955bd3084adca6344e5be20a22cb2cd2", "generation_seconds_batch": 21.80526730895508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.522135317325592, "target_z": 0.09765623185212371, "ce": 5.8875885009765625, "genuineness": 3.9299514293670654, "identity": 0.6482945680618286, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b5e0c806fa77b35c3b68b8bb9dd54a1fcc89d235f44b569e4e4c73003c66dafe.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "b64b90a4642575e327133a89ca9bd530413077e8de42b1c0bf1b2a4de96fd879", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a0806504caaf959c0458ac5247c0c11d6fe2d0ce31e184980d3730af47e5f015", "generation_seconds_batch": 18.586512758978643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.900118350982666, "target_z": 2.0156249274084947, "ce": 6.292664527893066, "genuineness": 4.011539936065674, "identity": 0.3484328091144562, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b64b90a4642575e327133a89ca9bd530413077e8de42b1c0bf1b2a4de96fd879.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "b6efd428eaec8c3a9f283dd5705548a03b970c6943bfb226cfe3a1bcfc9d2603", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b53ae9d540c23264874a04b4878e608b56ab2492a118eaca7b39d54698aa0d39", "generation_seconds_batch": 24.249415374011733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.911344289779663, "target_z": 2.03124993777871, "ce": 6.213237762451172, "genuineness": 4.193545341491699, "identity": 0.5245369672775269, "hypothesis": "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_Elation/b6efd428eaec8c3a9f283dd5705548a03b970c6943bfb226cfe3a1bcfc9d2603.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "b70145f8f82d07a4e1db1027b4a87c29d26d961ccfb9fb8ccb624fb00973e51d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8bec07713f08f860e51e580c452d2fea269845e8d7c1b69020dd5a7f757f16fc", "generation_seconds_batch": 24.166899693082087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5070505142211914, "target_z": 0.0766601967586524, "ce": 6.078212261199951, "genuineness": 3.7542223930358887, "identity": 0.23578083515167236, "hypothesis": "The 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_Elation/b70145f8f82d07a4e1db1027b4a87c29d26d961ccfb9fb8ccb624fb00973e51d.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "b739f74d0fc830612ca231516c42e8da5acde8b061e917eb159f0985d817943b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9a5749d5047bd2fac8bb64c64153075385aaa6e94fb1018f81f5c05266bfe058", "generation_seconds_batch": 21.85982440900989, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3379297256469727, "target_z": 2.625, "ce": 5.974957466125488, "genuineness": 4.193545341491699, "identity": 0.7470027208328247, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b739f74d0fc830612ca231516c42e8da5acde8b061e917eb159f0985d817943b.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": "b768bf57170dcb03daf2d8e9fe44ed0765299c02d7359602cd70a616faf1c116", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "babd647fcdb4e625c1f4cec0453c6a104ce5c0cc58650efabcc29bc463233a65", "generation_seconds_batch": 16.822991678956896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16009902954101562, "target_z": -0.40625002074043004, "ce": 6.300607204437256, "genuineness": 4.030367851257324, "identity": 0.4265759587287903, "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_Elation/b768bf57170dcb03daf2d8e9fe44ed0765299c02d7359602cd70a616faf1c116.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "b7833b8725e711035c1789b1224fa6770f3dd5d2cf9bc5bfeb2a0cf703240877", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2c74127c7c10cb5478c29abcc15b8a5d608ecf9958f53afc796351751f5ec7c3", "generation_seconds_batch": 22.81350063800346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9543336629867554, "target_z": 0.6992187162968012, "ce": 5.9431867599487305, "genuineness": 4.030367851257324, "identity": 0.5460917949676514, "hypothesis": "Ik 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_Elation/b7833b8725e711035c1789b1224fa6770f3dd5d2cf9bc5bfeb2a0cf703240877.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "b7b0e1225b31a050910cacdee5dce6e59ac92a3e8b881ae463b1222498c092f2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "feae968c1c16b94cc9300801fee6d01cd65f84b6f19c54c1c03d95151d303393", "generation_seconds_batch": 17.47067705099471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.596126079559326, "target_z": 2.984374906668065, "ce": 6.173524379730225, "genuineness": 4.118232727050781, "identity": 0.6088273525238037, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b7b0e1225b31a050910cacdee5dce6e59ac92a3e8b881ae463b1222498c092f2.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "b8504bdc7f316ea7cfbb4240da426482cab509d8d3f5aa3176dbee8983f988d5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1d94f33fe0d1a37f3a4cbf72624ce565edf6a6d2de28a8ae9e910cc547100e7b", "generation_seconds_batch": 22.549619148951024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5352756977081299, "target_z": 1.5078125881468276, "ce": 6.149696350097656, "genuineness": 3.6977379322052, "identity": 0.518784761428833, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro de la casa.", "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_Elation/b8504bdc7f316ea7cfbb4240da426482cab509d8d3f5aa3176dbee8983f988d5.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "b8d53d7c61f8204869ccf5c5ac6ad218012938566cfe90c5355bc4547990341e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "69d0eae91907552ef65f6b78f0346ffda276e15b5a0122d54ff4092ed38b8ad3", "generation_seconds_batch": 28.007873861002736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.258455991744995, "target_z": 3.90624985481699, "ce": 6.229123115539551, "genuineness": 4.118232727050781, "identity": 0.5458977222442627, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b8d53d7c61f8204869ccf5c5ac6ad218012938566cfe90c5355bc4547990341e.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": "b8ddd5d371d5995bc1aed3182350e60d5c87c13fd8beb49dec86c959095ab51d", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a52e4e7ecdc311ae7fc57918ead54465f4d5ab7043a38877ae5ced4f30e21666", "generation_seconds_batch": 18.874524860992096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5838779211044312, "target_z": 0.18359370592658616, "ce": 6.229123115539551, "genuineness": 4.344170093536377, "identity": 0.5898756980895996, "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_Elation/b8ddd5d371d5995bc1aed3182350e60d5c87c13fd8beb49dec86c959095ab51d.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "b91cf51f87ec96d82f4dcfcd07e5a1f5c649e50bdb2c43bb1f5394c4f491c47c", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fb032f20528b759084e80c58379ca02354a2a369335565a2495385e5007636ff", "generation_seconds_batch": 16.544862687936984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29621344804763794, "target_z": -0.21679689444415315, "ce": 6.24500846862793, "genuineness": 4.055472373962402, "identity": 0.6367418766021729, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b91cf51f87ec96d82f4dcfcd07e5a1f5c649e50bdb2c43bb1f5394c4f491c47c.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "b954d96b9388edd7ea9e8967d2f7309603a3cc9b7ccb834dbe0cdab9f192c541", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0ff8e77b098a9f28b8e8335cecd643115957298ff6ba4c8a23d826db834898c2", "generation_seconds_batch": 23.031228719977662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6699867248535156, "target_z": 1.6953123807425272, "ce": 6.38797664642334, "genuineness": 4.557555198669434, "identity": 0.6743375062942505, "hypothesis": "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_Elation/b954d96b9388edd7ea9e8967d2f7309603a3cc9b7ccb834dbe0cdab9f192c541.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "b9b5ebffc7efec21ae745004d792979e6eee21bf4690547bc6952dd79a0789b3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2eea92c8c54e36e569656c573bdc0be428822940c34d7b57fb9135cdb5032965", "generation_seconds_batch": 23.267392192035913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6807016134262085, "target_z": 0.31835937888883065, "ce": 6.348263263702393, "genuineness": 4.344170093536377, "identity": 0.5020131468772888, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/b9b5ebffc7efec21ae745004d792979e6eee21bf4690547bc6952dd79a0789b3.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "b9d5af7ab9bb2a3c4df508417ef020ecad63f70fc03705f4770965b2ed0f4b2e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39aeb231df12ebfbdb432792ac8d5bc9509044a2b9ef6478951f76130f349f1d", "generation_seconds_batch": 16.604435968096368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6073520183563232, "target_z": 2.99999991703828, "ce": 5.744620323181152, "genuineness": 3.735394239425659, "identity": 0.5739144682884216, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás bien.", "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_Elation/b9d5af7ab9bb2a3c4df508417ef020ecad63f70fc03705f4770965b2ed0f4b2e.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "ba03d86cf592fce1c5929730d9c09fb7611bd74c4ddacd5643a7564141d15a73", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7f77e920f207c77eb63c1ea2a7dcba4c47d3d1edf0e53de5f0cf8dca806d2d96", "generation_seconds_batch": 25.189624635968357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2499064952135086, "target_z": -0.28125, "ce": 6.24500846862793, "genuineness": 4.582659721374512, "identity": 0.6673727631568909, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ba03d86cf592fce1c5929730d9c09fb7611bd74c4ddacd5643a7564141d15a73.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "ba1b6e02c6c178099f1e111ced3c1b27673c65cabbd8362b9655b78e176251fc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "59fb0e1f24b79b6adee8ade803cb9f3069dc9749e2844a577a2b867af64f9a27", "generation_seconds_batch": 23.08792493492365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5035423636436462, "target_z": 0.07177731879667011, "ce": 6.24500846862793, "genuineness": 4.306513786315918, "identity": 0.4043528437614441, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ba1b6e02c6c178099f1e111ced3c1b27673c65cabbd8362b9655b78e176251fc.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "ba6e08b62ad61b79179c30f5e9db4f02a180635b1d75b677818afbe03287d1a7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "42f7595e5140f9099bd073e088586645bff5c5e7a0dd18dc2eb0d1dec2b4df66", "generation_seconds_batch": 27.290725592058152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2490143775939941, "target_z": 1.109374989629785, "ce": 5.879645347595215, "genuineness": 3.8797430992126465, "identity": 0.3718234896659851, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ba6e08b62ad61b79179c30f5e9db4f02a180635b1d75b677818afbe03287d1a7.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "a17c195785130d016b536407b345fa97e6ae6f59a0de209393028bad5a986de6", "generation_seconds_batch": 18.686592967016622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1516796052455902, "target_z": -0.41796873703723125, "ce": 6.284721851348877, "genuineness": 4.6203155517578125, "identity": 0.7116204500198364, "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_Elation/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "bad05bb1d2aa1989ac2d4e1c4b6408f02060349448f565bef1a477d03d1ba974", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6e8faaf611c95df0d154c035bfee2ad5a3bd8aaffb528e43fc97ba76fbb8a95a", "generation_seconds_batch": 22.97731975791976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.708385467529297, "target_z": 3.140625010370215, "ce": 5.982900142669678, "genuineness": 3.9173994064331055, "identity": 0.3479658365249634, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bad05bb1d2aa1989ac2d4e1c4b6408f02060349448f565bef1a477d03d1ba974.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "bb0326e40ba43059b3c988540eb124706db57d58b734915c0ddf618e022d8889", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ba03c9234a2253789a59cf91c09698efe8e9115d41ad4f7862341615a43b227c", "generation_seconds_batch": 16.550164362066425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3439236879348755, "target_z": -0.15039060037073934, "ce": 6.292664527893066, "genuineness": 4.331617832183838, "identity": 0.5238596200942993, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bb0326e40ba43059b3c988540eb124706db57d58b734915c0ddf618e022d8889.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "bb3de5561ce6e9b6391b4ef6bda0093766984f7b9d38e76f29f1a96fd7123aee", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "df27132f6a9f6a9f94681d0b0daba0ff80a5efbb29daae46f4e82627561f8222", "generation_seconds_batch": 21.180912518990226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0385282039642334, "target_z": 0.8164062940734138, "ce": 5.895530700683594, "genuineness": 3.9299514293670654, "identity": 0.7786604762077332, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ram. 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_Elation/bb3de5561ce6e9b6391b4ef6bda0093766984f7b9d38e76f29f1a96fd7123aee.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "bbc522b27a96550dc697bbe20ca9f67fbb5146a04ffc9c29e2886097e70c2a3e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc10a313101832b83d67d1f7fa8a3b2f2a62be7bc3c5d005281d65f6ca840eb2", "generation_seconds_batch": 23.503454128978774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4061774015426636, "target_z": 1.328124968889355, "ce": 5.974957466125488, "genuineness": 3.7793264389038086, "identity": 0.45197245478630066, "hypothesis": "The 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_Elation/bbc522b27a96550dc697bbe20ca9f67fbb5146a04ffc9c29e2886097e70c2a3e.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "bc111ca5435e22a78368ac8fdf569d8b008176de0c1a800e527e273c0adb540c", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fca6f9dc4cc0c0a02a4e91ed35ab58d7ba4d9997c025eb8bfff44ef19050bfb9", "generation_seconds_batch": 18.547662094933912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05625918507575989, "target_z": -0.5507812422223387, "ce": 6.1894097328186035, "genuineness": 4.149612903594971, "identity": 0.6126041412353516, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bc111ca5435e22a78368ac8fdf569d8b008176de0c1a800e527e273c0adb540c.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "bc4d569473fb536ee7ea0f46bd68e72079e63a7d131cc8de0c1edefa0d2c9540", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "19edda6f2072fb70fb7cc1e37f6ab53eacacdb4b05bb1d964e21e4cf80a915c8", "generation_seconds_batch": 22.421434079064056, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2714662551879883, "target_z": 1.140625010370215, "ce": 6.300607204437256, "genuineness": 4.331617832183838, "identity": 0.5558286309242249, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bc4d569473fb536ee7ea0f46bd68e72079e63a7d131cc8de0c1edefa0d2c9540.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "bc4f9d7f04c9654f02eb26adc75855b6a809c5a9d2df8171ff9897b6c7afec19", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2902f88245dd81cb193726154ba9f99b5cb76eff2bbe04f832aca40bee0adaba", "generation_seconds_batch": 16.241332683013752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1911003589630127, "target_z": 3.8124997925956996, "ce": 5.593709468841553, "genuineness": 3.8044304847717285, "identity": 0.6367983818054199, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bc4f9d7f04c9654f02eb26adc75855b6a809c5a9d2df8171ff9897b6c7afec19.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": "bc8c847b3d5940fbbf191130a8dabe7e0257965032a314c9d36a331fd4e99597", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b6b267a9e350be6f964a7aefa86def5d8058cedbd1cb1f8f3982f682b98c50a", "generation_seconds_batch": 24.2145151339937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6475348472595215, "target_z": 1.6640623600020972, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.6596506834030151, "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_Elation/bc8c847b3d5940fbbf191130a8dabe7e0257965032a314c9d36a331fd4e99597.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "bce7b263584e2f1858477256de83cf39497efae6160b0f3243d9344c7d904773", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "75cec7401bfed508f46cad3f3a014c83f0b5e25761363cfc7addc45cdd0c9e3e", "generation_seconds_batch": 14.945116931921802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7878592014312744, "target_z": 1.8593751555532252, "ce": 6.062326908111572, "genuineness": 4.231201171875, "identity": 0.5009305477142334, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bce7b263584e2f1858477256de83cf39497efae6160b0f3243d9344c7d904773.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": "bd06232b4a384d1a6e476d553392cd1f7b0f726d45c06b4b974913eb7024cde6", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "094ccb68517ec7a6a3668b96f6b1c51c121c746963fa04864f82f2156079ffad", "generation_seconds_batch": 24.940343503956683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6196606159210205, "target_z": 0.2333984472220766, "ce": 6.173524379730225, "genuineness": 4.111956596374512, "identity": 0.5340270400047302, "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_Elation/bd06232b4a384d1a6e476d553392cd1f7b0f726d45c06b4b974913eb7024cde6.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "bd784909a714bf0f023171597b8231b3268093fb8a11352f31801baa976f1e88", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a1695273d51bfd5478c5d32bed9e90a3f85a28e0fa2960b51376b575907bffed", "generation_seconds_batch": 24.249415374011733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2818000316619873, "target_z": 2.546874948148925, "ce": 6.006728172302246, "genuineness": 3.9048471450805664, "identity": 0.3058064579963684, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bd784909a714bf0f023171597b8231b3268093fb8a11352f31801baa976f1e88.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "bda54550efdb6f7322435fae707f6efeb811519431b4b5a61bd860709413a4fa", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7409c12ade5c1bf0fb053148aee766af932a862b9a1ebbc5bf3eecbd590d78b1", "generation_seconds_batch": 24.679392969002947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0011518001556396, "target_z": 2.15625002074043, "ce": 5.927301406860352, "genuineness": 4.105680465698242, "identity": 0.3413202166557312, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bda54550efdb6f7322435fae707f6efeb811519431b4b5a61bd860709413a4fa.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "bde2419cb91a8902aa7a23d09f91a3e46fc3a08f60cafd29a7560338e331dab1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a0f6e3118dc375b01bc54e9ae75b0bc92fd715cd91aeaf8ab4bf8dae19031ea6", "generation_seconds_batch": 20.10488822706975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9225702285766602, "target_z": 2.046874948148925, "ce": 6.205295085906982, "genuineness": 4.168440818786621, "identity": 0.46043866872787476, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête? 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_Elation/bde2419cb91a8902aa7a23d09f91a3e46fc3a08f60cafd29a7560338e331dab1.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "beba9c875ad6516d8dfd31718af77f37466fb07052f3da8782350b500fa14f66", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "87958a3c8c7afb44718310cc7a08b09e3a8b85eec0adbcc335f3700e6e89ba6e", "generation_seconds_batch": 16.50060599599965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7878592014312744, "target_z": 1.8593751555532252, "ce": 6.125868320465088, "genuineness": 4.432034492492676, "identity": 0.6451830267906189, "hypothesis": "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_Elation/beba9c875ad6516d8dfd31718af77f37466fb07052f3da8782350b500fa14f66.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "bf428e46860e0328b0baaff9055ff3865b7a605f059e690f297b32892f47d671", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d1c891b33886cae53755835e92d089344f26aff2ce10d96b78dad5686abb6403", "generation_seconds_batch": 20.54833714396227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7981927394866943, "target_z": 3.2656247614850544, "ce": 5.847874641418457, "genuineness": 4.111956596374512, "identity": 0.5117784738540649, "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_Elation/bf428e46860e0328b0baaff9055ff3865b7a605f059e690f297b32892f47d671.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "bfa05c356d59528cee194bef39e8ea3497e265d983151d7bbe11367a67abcc46", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb58496bbcbd31fa9f56494d95dec9d89a961d21de9438eb0201d24500846d10", "generation_seconds_batch": 21.82300838199444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4735329151153564, "target_z": 1.4218748651872049, "ce": 6.395919322967529, "genuineness": 3.898571252822876, "identity": 0.43851593136787415, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bfa05c356d59528cee194bef39e8ea3497e265d983151d7bbe11367a67abcc46.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "bfe9bfee4b7ad1391af9fdf3f6efcf53eebb1094f2c1017a9cfcf81ddc6ce6b4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "df6e6bd27b3474dff369fdd78693d19efddc974d4c75845423d6f5488cca7f7c", "generation_seconds_batch": 22.68844109599013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2546273469924927, "target_z": 1.1171874948148925, "ce": 6.268836498260498, "genuineness": 4.15588903427124, "identity": 0.8156437873840332, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/bfe9bfee4b7ad1391af9fdf3f6efcf53eebb1094f2c1017a9cfcf81ddc6ce6b4.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "c07fa8b8b557e71fb9ffcaebed9ae5142ee8f95b754e997f87460ae2c6f1b6ef", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bf5d7cbebb1aad2c4a8dddc9a699bcd12e5f5cded6ee406ebb6f0e17df5fad1d", "generation_seconds_batch": 23.292100145015866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28779399394989014, "target_z": -0.2285156522218144, "ce": 6.221180438995361, "genuineness": 4.362998008728027, "identity": 0.4107549786567688, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c07fa8b8b557e71fb9ffcaebed9ae5142ee8f95b754e997f87460ae2c6f1b6ef.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": "c099568bafa58e623f78d8b48424fd40a0ec32e96438e9cc0f6b7c5c564cd43c", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0c52386f67a0d3579976c713b96cd5f487228e60b2ce546db54ca27fa4e5687", "generation_seconds_batch": 16.90012120793108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06187215447425842, "target_z": -0.5429687370372313, "ce": 6.268836498260498, "genuineness": 4.2374773025512695, "identity": 0.40602490305900574, "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_Elation/c099568bafa58e623f78d8b48424fd40a0ec32e96438e9cc0f6b7c5c564cd43c.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "c0c8abacf04186a86cc9b4657ca277189233ad949e74a7db4aaae8efe22e59bb", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "759ffee8759034944e1355838ed17de750e5e0db5a40f941ec420b51e24e7a3b", "generation_seconds_batch": 21.774218300008215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9010105133056641, "target_z": 0.625, "ce": 6.0146708488464355, "genuineness": 4.105680465698242, "identity": 0.012967104092240334, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c0c8abacf04186a86cc9b4657ca277189233ad949e74a7db4aaae8efe22e59bb.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "c0d32ac348efc302bbc3d257aa770d7875473a2412b550da1d2e6ff1cc87e5ff", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f63a41b4b4cae414163b862011dcf87599ec0bae35d7a088395b1aab33ee539b", "generation_seconds_batch": 22.531889655045234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1919925212860107, "target_z": 2.421874865187205, "ce": 5.752562999725342, "genuineness": 3.835810661315918, "identity": 0.6185559034347534, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c0d32ac348efc302bbc3d257aa770d7875473a2412b550da1d2e6ff1cc87e5ff.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "c0fea656082279e83de018f1e25d2273e48227f26b01f87475e23e0a9591ab75", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b5754798bfd14f7cfad821ceed56e25c4315bc76d5ac60463620b432298ada18", "generation_seconds_batch": 23.503454128978774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0693994760513306, "target_z": 0.859374989629785, "ce": 5.824047088623047, "genuineness": 3.6914620399475098, "identity": 0.5979286432266235, "hypothesis": "The 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_Elation/c0fea656082279e83de018f1e25d2273e48227f26b01f87475e23e0a9591ab75.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "c15a8d13a0bc873ef550d3ace923c8a51a5b8a0c041a30e48da42a2a20c354ab", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "16820da889d2944393bf3ae1688730cd4f08374aab6a7f32e52fc2e314b96b49", "generation_seconds_batch": 16.544862687936984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.383725643157959, "target_z": 1.296875114072365, "ce": 6.181467056274414, "genuineness": 4.337893962860107, "identity": 0.5697177648544312, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c15a8d13a0bc873ef550d3ace923c8a51a5b8a0c041a30e48da42a2a20c354ab.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "c1c92011f56830607ff324a4d0118bb1b99178a0dbfc62cae9eb6f1fc35ce17e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "01f77e4b43baf92b41a5180ba42f6bc0c54c8e257c0dba8cf6f72f10a7e60712", "generation_seconds_batch": 20.298911933903582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7036645412445068, "target_z": 1.7421874118531724, "ce": 5.629451274871826, "genuineness": 3.785602569580078, "identity": 0.647006094455719, "hypothesis": "La puerta sigue abierta, sigue adó tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c1c92011f56830607ff324a4d0118bb1b99178a0dbfc62cae9eb6f1fc35ce17e.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "c31a8154cfded0c261194ece299d870bbadd9efc2dd24f369accb56e5df0f6a0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3b5d0e5101d696f65f609e143430730c943d029816b39431a1f3de50ed32f97c", "generation_seconds_batch": 22.992968678940088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21342222392559052, "target_z": -0.33203124222233876, "ce": 6.117925643920898, "genuineness": 4.118232727050781, "identity": 0.7248084545135498, "hypothesis": "La porte 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_Elation/c31a8154cfded0c261194ece299d870bbadd9efc2dd24f369accb56e5df0f6a0.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2800290c6e613e7739a3731fdd82c774214f6fcf1c7adcaf9bf302a7513d917", "generation_seconds_batch": 18.548167441040277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16430875658988953, "target_z": -0.4003906418515994, "ce": 6.062326908111572, "genuineness": 4.444586753845215, "identity": 0.6050054430961609, "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_Elation/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "c3e208752da90c9b49567bdae89da32e67cc5d1bfe64f3acb6bbb1ab97be96b3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "38f5c065bdc70dde6c807aed92d3a0013970f65bc1e8d7861c2374828515e8f8", "generation_seconds_batch": 20.965210031019524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7606863975524902, "target_z": 0.42968753629575257, "ce": 5.982900142669678, "genuineness": 4.331617832183838, "identity": 0.6485158205032349, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c3e208752da90c9b49567bdae89da32e67cc5d1bfe64f3acb6bbb1ab97be96b3.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": "c409ed6e02de7b30756eb5bfdd4e3c830e92f55c50d04336f67fb70bf204dcde", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c80f6d7fb14b626e31db726cf00afbbc859120779b50d884afca6109e0a37103", "generation_seconds_batch": 22.24783914501313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3649722933769226, "target_z": -0.12109374740744624, "ce": 6.252951145172119, "genuineness": 4.293961524963379, "identity": 0.3699709177017212, "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_Elation/c409ed6e02de7b30756eb5bfdd4e3c830e92f55c50d04336f67fb70bf204dcde.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "c4901e846fd5ce2a501aa110fc1e02efb7791e9eeb9ef79bc20b9c87260ec3a4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b0fe2a9706563ee996b41416b1853f492ec00a887e0adcd10444fc6393afb022", "generation_seconds_batch": 16.925982574932277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9683660864830017, "target_z": 0.71874997925957, "ce": 6.141753673553467, "genuineness": 4.256305694580078, "identity": 0.22818803787231445, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c4901e846fd5ce2a501aa110fc1e02efb7791e9eeb9ef79bc20b9c87260ec3a4.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "a6e4f60b8da25c4cb9f5d5ead5174c536db1f93f56209eb6e4aff4ce4ed59a2f", "generation_seconds_batch": 18.258536695037037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15869581699371338, "target_z": -0.4082031055558468, "ce": 6.300607204437256, "genuineness": 4.369274139404297, "identity": 0.6132426261901855, "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_Elation/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "c4b063a880e5c85d206b717730611451d1b14fd86781141c8af672aa72a8ddc7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5f590ad74b35b2438a8bf6c20b924a3347615bc93fae1a3933b6cfd49578a18e", "generation_seconds_batch": 24.844967092038132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41619059443473816, "target_z": -0.04980469981463033, "ce": 6.0146708488464355, "genuineness": 4.061748504638672, "identity": 0.48421236872673035, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c4b063a880e5c85d206b717730611451d1b14fd86781141c8af672aa72a8ddc7.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "c595d335bb6e86c905c46fc108ddbbdc5e58d33052ffb0c5247a990d860f6f40", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e31f30c27280dcb9183214deb6b51f045c3cdfb107cd2ee1d98a0d4afb602f8f", "generation_seconds_batch": 23.080368431052193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16992172598838806, "target_z": -0.3925781366664919, "ce": 6.09409761428833, "genuineness": 4.319066047668457, "identity": 0.5784116983413696, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c595d335bb6e86c905c46fc108ddbbdc5e58d33052ffb0c5247a990d860f6f40.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "c60da70affb01af2510b4fde548d508ab94b407569ace5c7f3daa622caeb8e79", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d8272f4c6e646229ffc47c6ba9d843f4026026257ec2c5639e3bc92dbedce164", "generation_seconds_batch": 16.576256926055066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5207321047782898, "target_z": 0.09570314703670692, "ce": 6.205295085906982, "genuineness": 4.381826400756836, "identity": 0.5858652591705322, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c60da70affb01af2510b4fde548d508ab94b407569ace5c7f3daa622caeb8e79.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "c61c3491beb14e7c638dbc1c7602d4d2ef4e954b6e157e050c0050907aec7e9e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1724aa2a90571af2d8b3e5d43125e88714f7d6beb9fe5281a8bd4a34779cf382", "generation_seconds_batch": 22.97731975791976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.090959310531616, "target_z": 2.28125010370215, "ce": 5.919358730316162, "genuineness": 4.149612903594971, "identity": 0.48308849334716797, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c61c3491beb14e7c638dbc1c7602d4d2ef4e954b6e157e050c0050907aec7e9e.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "c631973f3800e33a8739431a34428a18f711633a9d05cafbd8ce7099ab0403de", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d44970f5773d76955fa840687c871b4e4abcfe578800e02cad8ac5c2d530dba2", "generation_seconds_batch": 22.12097177701071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2751648426055908, "target_z": -0.24609374740744624, "ce": 6.260893821716309, "genuineness": 4.086852550506592, "identity": 0.2677891254425049, "hypothesis": "The 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_Elation/c631973f3800e33a8739431a34428a18f711633a9d05cafbd8ce7099ab0403de.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "c68f52e43e1f14db52d5cf9db9c013888da137ba165aa37eb1035a1dfbe5dfee", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0edfe1401e5d530b2ec8ef70b77c87f5fae2ec4451163c7d65f61bd543129043", "generation_seconds_batch": 23.151798023027368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6147492527961731, "target_z": 0.22656248444467747, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.8043349981307983, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c68f52e43e1f14db52d5cf9db9c013888da137ba165aa37eb1035a1dfbe5dfee.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "c7a8a3bb9680e2676c476d422cb18440fff92fbfd97296474813a9a84a167c48", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d1ab31afcc6d81449419093c14a282d6c631e0290f501d9905f220537bfffec", "generation_seconds_batch": 21.774218300008215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.552114486694336, "target_z": 1.5312499377787099, "ce": 6.078212261199951, "genuineness": 4.13078498840332, "identity": 0.4839525520801544, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c7a8a3bb9680e2676c476d422cb18440fff92fbfd97296474813a9a84a167c48.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "de06c7e5c77000aec45029775df4f506fdc86a29c6c240eab8d83663102517e5", "generation_seconds_batch": 17.04971778905019, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4386424720287323, "target_z": -0.0185546790742003, "ce": 6.23706579208374, "genuineness": 4.369274139404297, "identity": 0.6383991241455078, "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_Elation/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "c82687b017ddccf393d3c076c63fd7278d53ee3f69f83e1aaa8f7a5336187b79", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dd39c369164fa4ad08a4ab03213eb27f33b0146cb8ff0a5f2f467098c9e53caa", "generation_seconds_batch": 16.998837611055933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9778077602386475, "target_z": 3.5156249274084947, "ce": 5.268059730529785, "genuineness": 3.6098732948303223, "identity": 0.1265619695186615, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c82687b017ddccf393d3c076c63fd7278d53ee3f69f83e1aaa8f7a5336187b79.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "c831647450fa6c4b955d9b6ea2040b2f4791d40397b030fa16f9f8995b7342a7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ef4e16acd524a3cc8287d65ecddf2899ef49493b401ad15b2be81704c57cef7e", "generation_seconds_batch": 22.067212685011327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4959847927093506, "target_z": 1.453124885927635, "ce": 6.086154937744141, "genuineness": 3.9299514293670654, "identity": 0.7255834937095642, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c831647450fa6c4b955d9b6ea2040b2f4791d40397b030fa16f9f8995b7342a7.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "c87b52aa40b38a4129ea081a2afe68c56c6cdb5c337ca76f70a0a74be49013d0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "189bdb045e1066930359b10d31a1361c1cf4f504c416a01da991675f36256674", "generation_seconds_batch": 23.99599607102573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.707493305206299, "target_z": 4.53124993777871, "ce": 5.168776512145996, "genuineness": 3.961331605911255, "identity": 0.5238041877746582, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c87b52aa40b38a4129ea081a2afe68c56c6cdb5c337ca76f70a0a74be49013d0.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "e52063d4774299743f92fb5d1e72a2eeb0061e459174d5937f2999a27b2b76fb", "generation_seconds_batch": 17.380560722085647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.036613792181015015, "target_z": -0.578125010370215, "ce": 6.419747352600098, "genuineness": 4.482243061065674, "identity": 0.34438076615333557, "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_Elation/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.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": "c8bd054df2f89ea086ad4cebd4cea83d2d3e46486469b678ccb81d8a7540a626", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59f876502e4d73ef85881e398e21b46ccd4853763e65efcd56c39a96fb853e77", "generation_seconds_batch": 21.401879413053393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1114966869354248, "target_z": 0.9179686955563712, "ce": 6.1020402908325195, "genuineness": 4.243753433227539, "identity": 0.4545961022377014, "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_Elation/c8bd054df2f89ea086ad4cebd4cea83d2d3e46486469b678ccb81d8a7540a626.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "c93cad7541e8a43168276131f4a3947cf659e2f6fb5f03cdfbfe02240304496f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "4392eecb3d80942a3a4e36a2a8cfba57f191095666933c5b8fedea11bf980c80", "generation_seconds_batch": 22.999835808062926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.719611406326294, "target_z": 3.15625002074043, "ce": 5.959072113037109, "genuineness": 3.672633647918701, "identity": 0.2987346947193146, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c93cad7541e8a43168276131f4a3947cf659e2f6fb5f03cdfbfe02240304496f.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "c94968edd0496f666bb43acc8d0e6725990be90ec8b978bd9d24657fc7487d40", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "357da017bd2f51eb93aef21900b886f12d844c9e9271e566299cbf3fad2df11c", "generation_seconds_batch": 16.97173994302284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9908179640769958, "target_z": 0.75, "ce": 6.062326908111572, "genuineness": 4.319066047668457, "identity": 0.5396829843521118, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c94968edd0496f666bb43acc8d0e6725990be90ec8b978bd9d24657fc7487d40.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "c9542b5e56bad78e8e3ec6ef6e390f3553c76a007aed1a3bdf92a6c136a11500", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "594ceecf573ada3389e88f5b31e315044c9c1e7455ed29d39f231ee9921b8d1f", "generation_seconds_batch": 22.549619148951024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4389631748199463, "target_z": 2.765625093331935, "ce": 6.125868320465088, "genuineness": 4.149612903594971, "identity": 0.4937208592891693, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro de la casa.", "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_Elation/c9542b5e56bad78e8e3ec6ef6e390f3553c76a007aed1a3bdf92a6c136a11500.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "c95e7c0b9c78a5b0374a2c10e2a8ab5e64f0826a889c0d9b3e82fb5f4a6e6baf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c43bd037de9e9444d78df778649d96759917b9fcb9ae8bc4151ad7f585a2ee57", "generation_seconds_batch": 17.0054526879685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2939181327819824, "target_z": 1.171875031110645, "ce": 6.395919322967529, "genuineness": 4.074300289154053, "identity": 0.4052773118019104, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/c95e7c0b9c78a5b0374a2c10e2a8ab5e64f0826a889c0d9b3e82fb5f4a6e6baf.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": "c9a68167b36b939f9753f2b5ebfd52e973079eb29ec8a0990006846374dfedfb", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cbacb93b83d963e956af7c559f9b803774aee6491e7897f09a0f9d054ae756e9", "generation_seconds_batch": 20.84394112508744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5712487697601318, "target_z": 0.16601561074095436, "ce": 6.24500846862793, "genuineness": 4.231201171875, "identity": 0.41916683316230774, "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_Elation/c9a68167b36b939f9753f2b5ebfd52e973079eb29ec8a0990006846374dfedfb.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "c9f049837e87e08897c66ce98583a9f82dcff6bf3a6214ef0a65f770b4741bf6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1471340a8d29a7f6cc4f44ac3dc03360a87d6af4b482571075d9ab3661f944a9", "generation_seconds_batch": 24.84633823495824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39514198899269104, "target_z": -0.07910155277792343, "ce": 6.24500846862793, "genuineness": 4.293961524963379, "identity": 0.572111964225769, "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_Elation/c9f049837e87e08897c66ce98583a9f82dcff6bf3a6214ef0a65f770b4741bf6.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "ca82dadde17b9323450821c3debd5dfe92975389c26906a05874eb89319528e8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c9d7b40f5f15f3271e5534a608cd9672faefe9e7717f5d9da6470e6547921b58", "generation_seconds_batch": 22.71909558097832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39829927682876587, "target_z": -0.07470702898151546, "ce": 6.149696350097656, "genuineness": 4.068024158477783, "identity": 0.38700294494628906, "hypothesis": "The 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_Elation/ca82dadde17b9323450821c3debd5dfe92975389c26906a05874eb89319528e8.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": "ca99e670a1a87c6a9859cbfd7f2d62821b1899ec724cf71ffddfa8b14896e32b", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I wrote the number on the envelope.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "98cac1fbafb6030012ce8381ea6a9a2b04b326d66560d38d37166ac8ca80b06b", "generation_seconds_batch": 23.022909080027603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.726116418838501, "target_z": 1.7734374325936024, "ce": 6.141753673553467, "genuineness": 3.6663577556610107, "identity": 0.5740824937820435, "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_Elation/ca99e670a1a87c6a9859cbfd7f2d62821b1899ec724cf71ffddfa8b14896e32b.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "caa9d870bd70d8d7e01b284c72beaff449804250b468f6c931302587009e0c66", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d67f8a2d98d1cbedc81cbc8ac02d69ce7abbbf660970758ade1ebf3d47983178", "generation_seconds_batch": 22.526827192050405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1686484813690186, "target_z": 3.78124977185527, "ce": 5.990842819213867, "genuineness": 4.111956596374512, "identity": 0.31922829151153564, "hypothesis": "I found the little box! It was beside the old window! We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/caa9d870bd70d8d7e01b284c72beaff449804250b468f6c931302587009e0c66.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "cb58b62ecc9481a1b9bada3d9ac6c36d4cf2349e286c83babb6b8b93cee05730", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7bf479fcbe502d91c9a9029fce9d6bee5cf2cd171665e5aff12940abb0d4bcf7", "generation_seconds_batch": 24.284459954942577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44671109318733215, "target_z": -0.007324233981253306, "ce": 6.284721851348877, "genuineness": 4.419482707977295, "identity": 0.706955075263977, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/cb58b62ecc9481a1b9bada3d9ac6c36d4cf2349e286c83babb6b8b93cee05730.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "cb86563e229be6e3f82a23b91bfd8584ed73b2ca547f6ae0af2ee49f16fe5b23", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7aa9548ec32172221a717013489715098c817742d895beee4627377298c05d21", "generation_seconds_batch": 17.590891978004947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1255290508270264, "target_z": 0.9374998755574198, "ce": 5.9431867599487305, "genuineness": 3.848362922668457, "identity": 0.6098691821098328, "hypothesis": "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_Elation/cb86563e229be6e3f82a23b91bfd8584ed73b2ca547f6ae0af2ee49f16fe5b23.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "cb9da7de256c91bce25fedf1e15527fee4bfb5605ef6e78ce1d4e1760f77010a", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "95c53a678e5c6b3e0a231463dfc54381a3b709e03ad02ae67c65d4c56df3cb29", "generation_seconds_batch": 17.62369119899813, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2050027698278427, "target_z": -0.34375, "ce": 6.149696350097656, "genuineness": 4.300237655639648, "identity": 0.5225754976272583, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/cb9da7de256c91bce25fedf1e15527fee4bfb5605ef6e78ce1d4e1760f77010a.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": "cc17a339c3baddf44ac7738d8b8f9d9cce00d22293d7707016dca8a5b382e8c0", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "438ef357783166bd255d5b543027b9d8ff4864626637eaf5873c41c846c68e5c", "generation_seconds_batch": 21.70226614899002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5502001643180847, "target_z": 0.13671875777766127, "ce": 6.252951145172119, "genuineness": 4.243753433227539, "identity": 0.489431768655777, "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_Elation/cc17a339c3baddf44ac7738d8b8f9d9cce00d22293d7707016dca8a5b382e8c0.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "cca7e80b2af3600dc4cc93b540111bd64cf1ee10bd6954e119c60c39504c25f7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fda12e49dd12322d64c5aa611ae8674a7726170e224ab697b50728459b5c3333", "generation_seconds_batch": 16.50060599599965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.236896276473999, "target_z": 2.484374906668065, "ce": 6.09409761428833, "genuineness": 4.231201171875, "identity": 0.5519793629646301, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/cca7e80b2af3600dc4cc93b540111bd64cf1ee10bd6954e119c60c39504c25f7.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": "cd046ec0085c0ecb8ce82c912107264b097cc8f3c939e833c0ead56096f3364d", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de4fe9145cea924b1b6f9139a59c2104846f200aebf14195a0fa5deee2648bf2", "generation_seconds_batch": 17.796131195966154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18255090713500977, "target_z": -0.375, "ce": 6.09409761428833, "genuineness": 4.444586753845215, "identity": 0.7836475372314453, "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_Elation/cd046ec0085c0ecb8ce82c912107264b097cc8f3c939e833c0ead56096f3364d.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "cd28d71cd66d0068ff97310fa8ff0be9e25327ef25bc8e7b8fac8eee5bfafb6c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4937ebae774e2908e5f3f872a45eaf2476ec96c5a8180c3eb1f74195ee71d001", "generation_seconds_batch": 27.50180923892185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7634928226470947, "target_z": 0.4335937059265862, "ce": 5.982900142669678, "genuineness": 3.6789097785949707, "identity": 0.31906670331954956, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/cd28d71cd66d0068ff97310fa8ff0be9e25327ef25bc8e7b8fac8eee5bfafb6c.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "cde48139cdfd2ce448024f7ec4c1fc19c77fadd288030fa1f15e5fb9a13c0a53", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4d40b1f235ded994fd9dffec568e2b9cff5546f8c90b63407b9b7ba1753cb718", "generation_seconds_batch": 17.991618843050674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.715782642364502, "target_z": 0.3671874948148925, "ce": 6.260893821716309, "genuineness": 4.174716949462891, "identity": 0.616897463798523, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/cde48139cdfd2ce448024f7ec4c1fc19c77fadd288030fa1f15e5fb9a13c0a53.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "ce5fd3b0a49ec89a1400749e122b364ef7e61f8aecb4a8d886d8523ee7e3f716", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f847f4fdba9c2e1b93ecd9eff398112b92bd696e399458f4b798e69c0509e93a", "generation_seconds_batch": 22.373601571074687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4614148139953613, "target_z": 2.7968747822254847, "ce": 6.086154937744141, "genuineness": 4.124508857727051, "identity": 0.6130990982055664, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ce5fd3b0a49ec89a1400749e122b364ef7e61f8aecb4a8d886d8523ee7e3f716.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "632af38c9cb3b417852ee7b6ee0f437a80b3b705e837574645f91312c6a24145", "generation_seconds_batch": 17.241437104996294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07871103286743164, "target_z": -0.5195312629627687, "ce": 6.483288764953613, "genuineness": 4.557555198669434, "identity": 0.5349882245063782, "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_Elation/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.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": "d047fc04f6fc3d634c45a3a7899b6bf02fa6dee5f07cdcecdaae72f5e643731f", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "877fa8e5d49d7d892253eef4f6e17b6e2ed83ecd0a85e2420486e7a05f4a55ae", "generation_seconds_batch": 23.359847342944704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7284117937088013, "target_z": 0.3847655900005243, "ce": 6.2767791748046875, "genuineness": 4.268857479095459, "identity": 0.7460880279541016, "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_Elation/d047fc04f6fc3d634c45a3a7899b6bf02fa6dee5f07cdcecdaae72f5e643731f.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "d077934f0e9bd7e097bac41245bfb4ff3482bd4ecb6612a05970e9e53550d741", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "64e9996e138244c15c80b1a8845db2953656997427fc4a88df105eab115fb4b9", "generation_seconds_batch": 16.463373410049826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.551222324371338, "target_z": 2.921874865187205, "ce": 6.141753673553467, "genuineness": 3.9927117824554443, "identity": 0.41660088300704956, "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_Elation/d077934f0e9bd7e097bac41245bfb4ff3482bd4ecb6612a05970e9e53550d741.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "d07d81a59d0088d625f069452edc79627fea74fd9c06a2d56ace4e8555376738", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03b207de8cb79bd78eded80906dbede8dc384636fd8543297e3c8a1051f90bb3", "generation_seconds_batch": 15.780030117952265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.266745388507843, "target_z": -0.2578125051851075, "ce": 6.0146708488464355, "genuineness": 3.798154592514038, "identity": 0.4857370853424072, "hypothesis": "The 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_Elation/d07d81a59d0088d625f069452edc79627fea74fd9c06a2d56ace4e8555376738.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "d0cbe2cd3afc9a3f63ff9338999798e98760d88ef27f777f36be4da1246fa68f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fb7367bc162fe2270b26d069a6b76b138f486f6d514e033d2b5fd4e645226c7b", "generation_seconds_batch": 17.01318338396959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9786999225616455, "target_z": 2.125, "ce": 5.967014789581299, "genuineness": 4.1998209953308105, "identity": 0.659673810005188, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d0cbe2cd3afc9a3f63ff9338999798e98760d88ef27f777f36be4da1246fa68f.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "d0cf137b5d81365ea84c179ca102aea4a57a789156a6616c1b0f55e458a31120", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ec9412f66b1370254463e1dcda4b2d02e31620bf276afa684527af66b3b5bbb5", "generation_seconds_batch": 21.93996504403185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1535940170288086, "target_z": 0.9765625674063976, "ce": 5.967014789581299, "genuineness": 3.8797430992126465, "identity": 0.5263992547988892, "hypothesis": "De deur 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_Elation/d0cf137b5d81365ea84c179ca102aea4a57a789156a6616c1b0f55e458a31120.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "d0dd4eb2ab4ae7ff0b254b724ce62772322686502a70be7004e8a67e58e47b2c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "35b632ebce309b533c18da77026f061d2189e189aba6a964e989d01b691379cf", "generation_seconds_batch": 22.26821272005327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5128238201141357, "target_z": 1.4765625674063976, "ce": 6.24500846862793, "genuineness": 4.2751336097717285, "identity": 0.4612279236316681, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d0dd4eb2ab4ae7ff0b254b724ce62772322686502a70be7004e8a67e58e47b2c.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "d0e432288634e7ad6cd79961362db726dc3f8da8e007a0cf1cf61de681bc1cd0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8fed1ac38d1f70c015e146d699c36cf7b4e8fab0cc4c1d03007cc585b9ab4765", "generation_seconds_batch": 23.23096597904805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7878592014312744, "target_z": 1.8593751555532252, "ce": 5.863759994506836, "genuineness": 4.13078498840332, "identity": 0.2923825979232788, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d0e432288634e7ad6cd79961362db726dc3f8da8e007a0cf1cf61de681bc1cd0.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "8dfd33eb59814dffbca1918a442177d0d44008e727d175e447f8efbc5611a346", "generation_seconds_batch": 19.52414163609501, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022581398487091064, "target_z": -0.5976562318521237, "ce": 6.356205940246582, "genuineness": 3.7291181087493896, "identity": 0.2758035361766815, "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_Elation/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "d168b561bab36cd2506706ff85e413a16e73928cbcfb01a2ab4f2085f55889d7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7e584273dd61c3b9e5133433dc971cedf595b007e33c6684396a4dde081b7a80", "generation_seconds_batch": 22.65333817899227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4342422485351562, "target_z": 1.3671874948148925, "ce": 6.125868320465088, "genuineness": 3.773050308227539, "identity": 0.33069756627082825, "hypothesis": "Ik 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_Elation/d168b561bab36cd2506706ff85e413a16e73928cbcfb01a2ab4f2085f55889d7.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "d1953e38a97297d20236c6b0ab4c593cf3ee7527b3703e152708d31504ddd385", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "52b8a0fc068b1cc2f6a7b458464702a53e6eb6c9ed3954c62ac25499b612ab89", "generation_seconds_batch": 21.9587020999752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3051440715789795, "target_z": 1.18750004148086, "ce": 6.078212261199951, "genuineness": 4.306513786315918, "identity": 0.6534644961357117, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d1953e38a97297d20236c6b0ab4c593cf3ee7527b3703e152708d31504ddd385.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "d1abe3484b6699c63d44436d271a49c34980c1afc13839a2968f7b6aa8f0ec75", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "98951a996ceaa0ac08e2b2538aeb7d4ab612de9631c1411b5512d85b28b5d1bb", "generation_seconds_batch": 23.57665981503669, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12501800060272217, "target_z": -0.4550781366664919, "ce": 6.181467056274414, "genuineness": 3.9550557136535645, "identity": 0.29465338587760925, "hypothesis": "The 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_Elation/d1abe3484b6699c63d44436d271a49c34980c1afc13839a2968f7b6aa8f0ec75.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "45755d10a2d5787d97ecdbe72c18ef64884ad0fa3064e021e5f948c113e715aa", "generation_seconds_batch": 17.446200608043, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1390504240989685, "target_z": -0.43554687370372314, "ce": 6.086154937744141, "genuineness": 4.582659721374512, "identity": 0.6553433537483215, "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_Elation/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "d236460c0320c969cf4a51e201e89a61894324f7785903770e0a76f8d8c31c68", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4129a2fb6e9044073e4ca887342b725ebcc810ae17cce21f9a3fa7ce13994676", "generation_seconds_batch": 22.26821272005327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8420743942260742, "target_z": 0.5429687785180913, "ce": 6.300607204437256, "genuineness": 4.099404335021973, "identity": 0.5620354413986206, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d236460c0320c969cf4a51e201e89a61894324f7785903770e0a76f8d8c31c68.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "d31002c3b989ab1b72ace9d28706a5c03f39660bc98addbd8e46d4896660eda1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "36336a374da6b0a02f6a4528ebd05d5a1c62b5fdc9a1b582833d0e4f58341018", "generation_seconds_batch": 24.19358698592987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0301086902618408, "target_z": 0.8046874533340325, "ce": 5.911416053771973, "genuineness": 3.973883628845215, "identity": 0.2135447859764099, "hypothesis": "De deur 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_Elation/d31002c3b989ab1b72ace9d28706a5c03f39660bc98addbd8e46d4896660eda1.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": "d357847aa9b85461ed4a9b56460e1424e005004921e93c431f6a288262e4073b", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4689eabd30cffe5d186419a78fe6b18cec7821081f2a0ccd607dbf34ed85456", "generation_seconds_batch": 23.28350764804054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26814863085746765, "target_z": -0.25585937888883065, "ce": 6.09409761428833, "genuineness": 4.18099308013916, "identity": 0.8240764141082764, "hypothesis": "La roue 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_Elation/d357847aa9b85461ed4a9b56460e1424e005004921e93c431f6a288262e4073b.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "d5614474e61e3ae260faac2114281a908b20a503d82239fb7176f152232d1903", "generation_seconds_batch": 16.586406468064524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3860208988189697, "target_z": -0.09179689444415316, "ce": 6.054384231567383, "genuineness": 4.394378662109375, "identity": 0.5424358248710632, "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_Elation/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "d4078f442854cb8b8d18e8cdeae7e06103c051a1a21d0fe2d5e33379a1094483", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e994346398f1a18413cfb2923dfebcbfea0f3d0a8ce296522345e2239827a6a", "generation_seconds_batch": 27.358089277986437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9553558826446533, "target_z": 3.484374906668065, "ce": 5.08339262008667, "genuineness": 3.6224255561828613, "identity": 0.08836168050765991, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d4078f442854cb8b8d18e8cdeae7e06103c051a1a21d0fe2d5e33379a1094483.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "d41e6b3639e38d2d39194de924734710b4db33a91a5d7c116908a223573117ca", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "90158d836c21919577788ce9cf2279417f63836afa5792b87693577b10df1484", "generation_seconds_batch": 22.687802717089653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.720503568649292, "target_z": 1.765625093331935, "ce": 6.046441555023193, "genuineness": 4.250029563903809, "identity": 0.5275981426239014, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d41e6b3639e38d2d39194de924734710b4db33a91a5d7c116908a223573117ca.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "d479f58d50737b9bc3b6a04d3747d066fd75095a872762110287d1433112f49a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53af244ee4d7b7862a7a16eaa19543cf529649d1df2d3b00a87e659d8f41dd05", "generation_seconds_batch": 16.92369428393431, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1592068672180176, "target_z": 0.9843749066680648, "ce": 6.3641486167907715, "genuineness": 4.017816066741943, "identity": 0.47768765687942505, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d479f58d50737b9bc3b6a04d3747d066fd75095a872762110287d1433112f49a.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "d4a3091cf1b1a59953f89e04dfaaa9d1908d120dce9701481c33b6996b70ca2e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fed38468352e3a49799c843e046231d6f79e2658731b95a616a848d89172d885", "generation_seconds_batch": 24.844967092038132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7990849018096924, "target_z": 1.8749998340765597, "ce": 5.855817794799805, "genuineness": 4.030367851257324, "identity": 0.2374078631401062, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d4a3091cf1b1a59953f89e04dfaaa9d1908d120dce9701481c33b6996b70ca2e.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "d4be134d83d9ef9f085def1c565b53cac5e6565704229ea755c701fbddb79161", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b7bb16f7e59e271898336c16335cd0a58d42fe2c5749ffb2ddca806543ea3ec2", "generation_seconds_batch": 17.69113864505198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5165223479270935, "target_z": 0.08984372666701622, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.5998260378837585, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d4be134d83d9ef9f085def1c565b53cac5e6565704229ea755c701fbddb79161.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "d4d9380533f1a44290b5ee6cef6417e5bdd98258493842c5ce042aacf8f393c9", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5d4a7a177677e56e700e5a1caa73f6404821ee5a70b5819da08cd2e716ab385c", "generation_seconds_batch": 22.4176809390774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6185779571533203, "target_z": 3.0156249274084947, "ce": 5.411027908325195, "genuineness": 3.6412534713745117, "identity": 0.04904819652438164, "hypothesis": "De deur 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_Elation/d4d9380533f1a44290b5ee6cef6417e5bdd98258493842c5ce042aacf8f393c9.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": "d52d1f916a748c1f1c025189031c196297b3daeb163335b329db14dde9705851", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a848d9007ad2c362f6597a1d2436956eb4526f9ff3f6b8b85f323d1d67ca5164", "generation_seconds_batch": 16.602132058003917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1839541494846344, "target_z": -0.37304687370372314, "ce": 6.395919322967529, "genuineness": 4.419482707977295, "identity": 0.6509102582931519, "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_Elation/d52d1f916a748c1f1c025189031c196297b3daeb163335b329db14dde9705851.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "d54fd782e233052404b87d520df6f571f8868d3a77aca94c96250349cea6ef26", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "17eaecf19da54f25c21b68c15f54be893c99fc35e0858066bba6f64334583e06", "generation_seconds_batch": 17.11703216598835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.307439386844635, "target_z": -0.20117188407393813, "ce": 6.078212261199951, "genuineness": 4.331617832183838, "identity": 0.6494015455245972, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d54fd782e233052404b87d520df6f571f8868d3a77aca94c96250349cea6ef26.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": "d55b7a85cf9de8763851cd28f27eb0bca20895d9790946217c24f6a305014d2e", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Someone moved the little blue chair.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d16d326b094ec6b6c8117c28a12e45f723256b93d1b00a8e857e0656102a63d", "generation_seconds_batch": 21.52861760603264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4566941261291504, "target_z": 1.3984375155553226, "ce": 6.205295085906982, "genuineness": 3.7667744159698486, "identity": 0.2937154173851013, "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_Elation/d55b7a85cf9de8763851cd28f27eb0bca20895d9790946217c24f6a305014d2e.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": "d56242184ae61543a8d5b889aed5ba20c00e903f83a0d35254b736d4416a02a0", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f03b130c98b167519708ca00545e8b69c4638b8ccfe9acdf7dd5e615608d99c9", "generation_seconds_batch": 21.854495859937742, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.041334629058838, "target_z": 0.8203124637042475, "ce": 5.990842819213867, "genuineness": 4.111956596374512, "identity": 0.6084985733032227, "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_Elation/d56242184ae61543a8d5b889aed5ba20c00e903f83a0d35254b736d4416a02a0.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "d58e687151cfbd519e12eeafecdd4f7cbe668555c3a47b9eeda364adaa5313e2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 130, "seconds_generated": 10.4, "mp3_sha256": "8f1023b59f2353871c4c2470b64c6953113f42dae9573520c33f4dc7452504c8", "generation_seconds_batch": 25.09075260499958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.416511297225952, "target_z": 2.7343750725915053, "ce": 5.855817794799805, "genuineness": 3.6098732948303223, "identity": 0.1546470820903778, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás viendo.", "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_Elation/d58e687151cfbd519e12eeafecdd4f7cbe668555c3a47b9eeda364adaa5313e2.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "d59a80e3880065d1306dfd22f3174a49721c28dc6859049252a635d41cfb125a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "174e367a9682e70865bcf7847fc50bf4bfb77a942579bd6a4b61b4b686876ad9", "generation_seconds_batch": 22.57544781593606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.911344289779663, "target_z": 2.03124993777871, "ce": 6.165581703186035, "genuineness": 4.281409740447998, "identity": 0.6458431482315063, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d59a80e3880065d1306dfd22f3174a49721c28dc6859049252a635d41cfb125a.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "d5a312a43ae96a681d3b637c2623dbb12a928b3686ffee6d6bdc9fcba227b521", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d94255d5c30263debaa3f1c10249d8a0f259d93bbfc8e2344fb9342dba4c33a7", "generation_seconds_batch": 22.033067221054807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.932904005050659, "target_z": 3.4531248859276347, "ce": 6.0146708488464355, "genuineness": 4.030367851257324, "identity": 0.4637488126754761, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d5a312a43ae96a681d3b637c2623dbb12a928b3686ffee6d6bdc9fcba227b521.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "d5c51802a3a42702d1169b23943a6dae5a9f3de89fe0101d423123b4f9133550", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "75e4787ccb54736954b8a16aa5a5267a26bce5abadf3d3dd4b6765c6774f4e61", "generation_seconds_batch": 22.970760873053223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4623069763183594, "target_z": 1.4062498548169897, "ce": 6.340320587158203, "genuineness": 4.293961524963379, "identity": 0.4478457272052765, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d5c51802a3a42702d1169b23943a6dae5a9f3de89fe0101d423123b4f9133550.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "d5cb29af20c42f49031b061a8bf76ab6fe15f817652800fb81a5721144b26fe0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "29a120c36e8ac5a9b2bb04e3e82f6aa93c0b707b2ff2c472d2e4e53266a3f7be", "generation_seconds_batch": 27.550083438982256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7597942352294922, "target_z": 1.8203124637042474, "ce": 6.181467056274414, "genuineness": 4.356721878051758, "identity": 0.6060736179351807, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d5cb29af20c42f49031b061a8bf76ab6fe15f817652800fb81a5721144b26fe0.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "d5e405a6f9c306c1e560b44c5aa729bb09201030c5be662b550fe94a2b4f464c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "77f1188351dfeb6074d8a289cbe466656600a05e5584ad559945663a1df09561", "generation_seconds_batch": 23.98640152195003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.343222051858902, "target_z": -0.1513671842593078, "ce": 6.221180438995361, "genuineness": 4.582659721374512, "identity": 0.6874875426292419, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d5e405a6f9c306c1e560b44c5aa729bb09201030c5be662b550fe94a2b4f464c.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "d6884a55e44e2f155dab15e3dbe7f0889f0e201be5c78cc5c816295b0d28ca9d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4f735ac9b334fb3e725ebae55aaae0b58052a1d0b24b94dee0d52dae8304c8ca", "generation_seconds_batch": 23.33231629501097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.888892412185669, "target_z": 1.9999999170382798, "ce": 5.756534099578857, "genuineness": 3.653805732727051, "identity": 0.47708481550216675, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken!", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/d6884a55e44e2f155dab15e3dbe7f0889f0e201be5c78cc5c816295b0d28ca9d.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": "d7e9a7193f08fcfe3ddcd94aa5605d12d22b5a9abdb63614c7b778f0459f7801", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4c5420bb023f1561b720f2f03e17ce579d5ee2278c181683f89713cdf83cddea", "generation_seconds_batch": 15.258758691954426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.568953514099121, "target_z": 1.5546876192574728, "ce": 6.499174118041992, "genuineness": 4.381826400756836, "identity": 0.4814518690109253, "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_Elation/d7e9a7193f08fcfe3ddcd94aa5605d12d22b5a9abdb63614c7b778f0459f7801.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "d92e64b51503037c33b33baf08d6cfc915ab9069c554361fe19bc3bc9968fbfd", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "83af36ac46c2dfcd40a3ae875780aec9f2e1f74919bbdaffeaf8bd02b9aef38d", "generation_seconds_batch": 16.260606224066578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.720503568649292, "target_z": 1.765625093331935, "ce": 5.982900142669678, "genuineness": 3.798154592514038, "identity": 0.41795122623443604, "hypothesis": "The 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_Elation/d92e64b51503037c33b33baf08d6cfc915ab9069c554361fe19bc3bc9968fbfd.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "da5338e8fadcd14a349b5ade4550ea698ff44a83e5d03694ecba806dff38c054", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a882978f29afd1befb87d6a396a798e4b7c813677d035fed03f8d09716ac65c0", "generation_seconds_batch": 16.168944587931037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6747076511383057, "target_z": 3.09374997925957, "ce": 5.919358730316162, "genuineness": 3.7542223930358887, "identity": 0.43062329292297363, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het al de raam. We kunnen er samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/da5338e8fadcd14a349b5ade4550ea698ff44a83e5d03694ecba806dff38c054.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "da7d7502462f14746a02d25c6399f95124352f4e5c4b7fc7508d0754448d040e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f93894271e507b62eeb80eb9ed5fef731a0b51cc9ae4a5ff6cf422edb9a4448b", "generation_seconds_batch": 23.45025293598883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.046055555343628, "target_z": 2.21875006222129, "ce": 6.1894097328186035, "genuineness": 3.9927117824554443, "identity": 0.5073191523551941, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/da7d7502462f14746a02d25c6399f95124352f4e5c4b7fc7508d0754448d040e.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "da9a81368fe314e9adbbbd7964aacb50a194d7f142a1f7817312d590e77f7eab", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1d12407b499a8e129aa2fa6098825a175fbc71cb891b9a9c458b72b9eea17b67", "generation_seconds_batch": 24.433201162028126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5015978813171387, "target_z": 1.4609375570361827, "ce": 6.427689552307129, "genuineness": 4.2249250411987305, "identity": 0.4808658957481384, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/da9a81368fe314e9adbbbd7964aacb50a194d7f142a1f7817312d590e77f7eab.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "dab3c11a7bd3e1ed8df20764285aa21dc95aa5f23954d97ed9b7fb6d6d847c2a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0909484b02b9b3b1c50aef9b325fc2e879db7c24856b644b5c7ab831582178e9", "generation_seconds_batch": 23.663636183948256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1358630657196045, "target_z": 2.34375014518301, "ce": 6.181467056274414, "genuineness": 4.469690799713135, "identity": 0.5849084854125977, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/dab3c11a7bd3e1ed8df20764285aa21dc95aa5f23954d97ed9b7fb6d6d847c2a.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9d25702d6d40a4fb88d55ff56bc949a26b959589999a1428c411bfbab3c16250", "generation_seconds_batch": 17.01676122599747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.036613792181015015, "target_z": -0.578125010370215, "ce": 6.427689552307129, "genuineness": 4.231201171875, "identity": 0.4777638018131256, "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "dc90aff65f05ba33d562a9094bf3a6e63d94a7c00c0ec688d1ede208ac621eb7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa8539839f1ccbad0c03fdd8c05d9d4f236596b4a48f6da980b4dbd85675c65e", "generation_seconds_batch": 23.99599607102573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.888000249862671, "target_z": 3.3906248444467746, "ce": 5.40705680847168, "genuineness": 3.9425034523010254, "identity": 0.5109354257583618, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay en el.", "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_Elation/dc90aff65f05ba33d562a9094bf3a6e63d94a7c00c0ec688d1ede208ac621eb7.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "dca3ff781c61de992b4f2a1c3e6a56abc67f1a50bcf98daf7889bac7b94defd3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "61641596adb16b860311eff68c451d09bcf3fa4a52173b65f32e86bea1fea0d7", "generation_seconds_batch": 19.97298199904617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.753289222717285, "target_z": 3.203125051851075, "ce": 5.49045467376709, "genuineness": 4.099404335021973, "identity": 0.40410056710243225, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay de...", "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_Elation/dca3ff781c61de992b4f2a1c3e6a56abc67f1a50bcf98daf7889bac7b94defd3.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": "dcfb717aa7f0f5e964dfa70779e2180e7169fa5a18173a7a642ab83f14cad7d3", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Someone moved the little blue chair.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9160f7619a54b29f795dde18220bed5045b264ed2b9828289efb00bc55eda555", "generation_seconds_batch": 20.33409830799792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27235835790634155, "target_z": -0.25, "ce": 6.38003396987915, "genuineness": 4.256305694580078, "identity": 0.4850004315376282, "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_Elation/dcfb717aa7f0f5e964dfa70779e2180e7169fa5a18173a7a642ab83f14cad7d3.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": "dd1929df3417bdfa571e3809e7096f4b394e213bd826a5e1f69c44c7d39ec528", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "762b4fb34ae6f9127e68541e46278ba7eef007046c5ad13763788ba8e5f89d9f", "generation_seconds_batch": 16.486820703954436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.145174503326416, "target_z": 0.9648437266670162, "ce": 6.292664527893066, "genuineness": 4.632867813110352, "identity": 0.7009876370429993, "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_Elation/dd1929df3417bdfa571e3809e7096f4b394e213bd826a5e1f69c44c7d39ec528.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "ddf41103a87ce5098492ea09bc219c1e2ed7b67edcadfc65de3088c392364b32", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3a503a209e8cc430a5734f7d96ad8dcb15c448a0526ed13a79ad7cb973350307", "generation_seconds_batch": 21.592055983026512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1349709033966064, "target_z": 3.7343750725915053, "ce": 5.8875885009765625, "genuineness": 4.068024158477783, "identity": 0.3211105167865753, "hypothesis": "I found the little box. It was beside the old window. We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ddf41103a87ce5098492ea09bc219c1e2ed7b67edcadfc65de3088c392364b32.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": "de40291f5099e58239ee59592c708997663ab66b4f23139a6d30623db517e5d5", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "98c2cbfa2fa7fa0b51612e1cb1f7a203c899885620eaaeab2d69b3c44793d329", "generation_seconds_batch": 16.655406868085265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05625918507575989, "target_z": -0.5507812422223387, "ce": 6.3641486167907715, "genuineness": 4.519899368286133, "identity": 0.7060604095458984, "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_Elation/de40291f5099e58239ee59592c708997663ab66b4f23139a6d30623db517e5d5.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "de7cd35d5d1ad78d084335e3cb1ff938be49492486bfc6c4c52e36b48c035042", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cc00e14ad7101ad2916a3eba674b4038510d81561abf5537507ed103222394cf", "generation_seconds_batch": 23.52139765699394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2041106224060059, "target_z": 1.046874948148925, "ce": 6.499174118041992, "genuineness": 4.13078498840332, "identity": 0.37571489810943604, "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_Elation/de7cd35d5d1ad78d084335e3cb1ff938be49492486bfc6c4c52e36b48c035042.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "dea54b827e32a0e2fc00dea2532e8c53abbeb11a8b0268f37e0ac2405c70b93d", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9ad3d46052ab76e12f4171cb803315ee95c38d24b6f3c21df8f17c1eb706fc2c", "generation_seconds_batch": 18.586512758978643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8383758068084717, "target_z": 1.9296875362957526, "ce": 6.141753673553467, "genuineness": 3.948779582977295, "identity": 0.4734070897102356, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/dea54b827e32a0e2fc00dea2532e8c53abbeb11a8b0268f37e0ac2405c70b93d.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": "df87037299179b2f3b87cf707bfec79a736659eb565b50513c4d068b1271ce1b", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b24abfb9b6f2a7cea37840a7323008c58277b774c2b25faf99b4a871e24cce8b", "generation_seconds_batch": 15.202546224929392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8112030625343323, "target_z": 0.5, "ce": 6.054384231567383, "genuineness": 4.017816066741943, "identity": 0.5796915888786316, "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_Elation/df87037299179b2f3b87cf707bfec79a736659eb565b50513c4d068b1271ce1b.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "dfb687281b03969dcb87a49c1212ea39674de8f339f561eb082bf6ff4f731868", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "02992c3fd92d0655b3b81d2123952966a1a31d36e53133a364a1d5bcb89c3749", "generation_seconds_batch": 17.012443554005586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7410410046577454, "target_z": 0.40234376814787626, "ce": 6.038498878479004, "genuineness": 4.049196243286133, "identity": 0.2726791203022003, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/dfb687281b03969dcb87a49c1212ea39674de8f339f561eb082bf6ff4f731868.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "e076c5c15a0370eb398fff128803154f3544ed850f4652531f72c9df55d2721f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d454043705660bdfe9c9c13aa13cebceb3477ed3611a911b00e4a99728cc1a0", "generation_seconds_batch": 23.255221355939284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2330676019191742, "target_z": -0.3046874948148925, "ce": 6.38003396987915, "genuineness": 4.262581825256348, "identity": 0.5485513806343079, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e076c5c15a0370eb398fff128803154f3544ed850f4652531f72c9df55d2721f.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "e0a9302c7402756442568f5006431e276938b7f6e16d5481a0d8835cdf834b04", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ae05c1585ca76664ec8dcfa976faf82a051a3b96ed580fe63f0c38c9edbded0c", "generation_seconds_batch": 22.86867048998829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1592068672180176, "target_z": 0.9843749066680648, "ce": 5.250188827514648, "genuineness": 3.6663577556610107, "identity": 0.36921894550323486, "hypothesis": "De deur 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_Elation/e0a9302c7402756442568f5006431e276938b7f6e16d5481a0d8835cdf834b04.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": "e10f46b6db15e3c570444263ee580067e3e34b0f0bd3f3fd81d6d9a96ba6dbc2", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "96b30f4ed7c60d8d3c8ad546a177f65c25e85867b952a23840df85a14a253e5b", "generation_seconds_batch": 22.24783914501313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7606863975524902, "target_z": 0.42968753629575257, "ce": 6.427689552307129, "genuineness": 4.356721878051758, "identity": 0.30034852027893066, "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_Elation/e10f46b6db15e3c570444263ee580067e3e34b0f0bd3f3fd81d6d9a96ba6dbc2.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "e1485182d2cbe57c3b11ccbbeadb970df6402d3bcc0d6920afad0a89dd60ce96", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "df8c996bb4a4c876287b2085e68ff5b58fcecae43c8355cf1c296b3ac0eb127f", "generation_seconds_batch": 22.738897978910245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9786999225616455, "target_z": 2.125, "ce": 6.141753673553467, "genuineness": 3.9425034523010254, "identity": 0.4614657759666443, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e1485182d2cbe57c3b11ccbbeadb970df6402d3bcc0d6920afad0a89dd60ce96.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "e18705a60d5528ebb6f330a0c4aebab0e3ac2775ab71d9150a0d323c6ca62bf1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b6b311fb5a3210a4a01459021df0e496909f95f3266f17e9c0513641e7a64f74", "generation_seconds_batch": 21.603425694047473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8159239292144775, "target_z": 1.8984375155553226, "ce": 6.252951145172119, "genuineness": 4.356721878051758, "identity": 0.4056472182273865, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e18705a60d5528ebb6f330a0c4aebab0e3ac2775ab71d9150a0d323c6ca62bf1.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "e18a1c8452ac20761c76a91249d72608997eeec5a87a64040e494fc0fc940e91", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4733455205faee7f6a459c7563bf30da2cfa1a2a69c52bce6736e536d7f5c2b9", "generation_seconds_batch": 24.45710303389933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.299531102180481, "target_z": 1.1796875362957526, "ce": 6.38003396987915, "genuineness": 4.118232727050781, "identity": 0.46185770630836487, "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_Elation/e18a1c8452ac20761c76a91249d72608997eeec5a87a64040e494fc0fc940e91.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": "e249303515e371fecab9e43c43bb435bb44e3a61dc13be0c4651fad2a842917a", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0bd360f4dfd6fbda96c388dc99f60fbd61dab5ba6f1243c94dd39639c1c6f065", "generation_seconds_batch": 17.62099951202981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6301848888397217, "target_z": 0.24804683222286306, "ce": 6.038498878479004, "genuineness": 4.369274139404297, "identity": 0.4805452227592468, "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_Elation/e249303515e371fecab9e43c43bb435bb44e3a61dc13be0c4651fad2a842917a.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "e26358d84adeba972e0c9a9499fb20c7b14179c87b109463cfe410f51ff0ffda", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0e8d492d845683ddaed340f62ad62a5eec014f9cb39d36c81a407fd970f32419", "generation_seconds_batch": 22.89549993898254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0114855766296387, "target_z": 3.56249995851914, "ce": 5.202532768249512, "genuineness": 3.9299514293670654, "identity": 0.40800464153289795, "hypothesis": "En que he entrado la cajita estaba junto a la ventana vieja. Podemos mirar juntos.", "wer": 0.4117647058823529, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e26358d84adeba972e0c9a9499fb20c7b14179c87b109463cfe410f51ff0ffda.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "e2b751039f5df8d0855cfa5e224d6ad0f3d331922c3bf7e20299c1048353efe5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2060bd451165f57e0e439949b2aae91fa86a63ef3a8272f94b9c983e4c650b67", "generation_seconds_batch": 24.31933836801909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8729456663131714, "target_z": 0.5859374740744625, "ce": 6.419747352600098, "genuineness": 3.8546390533447266, "identity": 0.44686365127563477, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e2b751039f5df8d0855cfa5e224d6ad0f3d331922c3bf7e20299c1048353efe5.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "e30d998a903f3ef8646aec778a9ee093b834b54f9e8880d468c8cd03fefa2813", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "953276398bc10fe65a3f10bc113a8bc06146a78c79e6e0db729db60dabce54dd", "generation_seconds_batch": 17.991618843050674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3668866157531738, "target_z": 1.2734374325936024, "ce": 5.919358730316162, "genuineness": 3.9425034523010254, "identity": 0.5651693940162659, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e30d998a903f3ef8646aec778a9ee093b834b54f9e8880d468c8cd03fefa2813.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": "e33499e3320ecfa594fbd26ea9432b6bebceca67cedfcf1af31ed983f1c65e05", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e4de2042d49b03295105823706debf5b5d90bf82582577d470633f44e6080aa9", "generation_seconds_batch": 16.267872247030027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2288578748703003, "target_z": -0.31054687370372314, "ce": 6.165581703186035, "genuineness": 4.425758361816406, "identity": 0.6361210346221924, "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_Elation/e33499e3320ecfa594fbd26ea9432b6bebceca67cedfcf1af31ed983f1c65e05.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "e33a2f19f1c3a1882aa5b2cc306b2fbb923c77ddb3b03060d26950fb5d818114", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bf3c18fcab1ca9b29dc448e391d376b86385a3177b10fd5c3f3a90d8161dd5ff", "generation_seconds_batch": 22.526827192050405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1911003589630127, "target_z": 3.8124997925956996, "ce": 5.808161735534668, "genuineness": 3.998987913131714, "identity": 0.4118879735469818, "hypothesis": "I found little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e33a2f19f1c3a1882aa5b2cc306b2fbb923c77ddb3b03060d26950fb5d818114.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "e3af275d824c1cd7f832c2df354e179b4199792814acbfeef5d243a7c067928e", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3d4879e4aee9494f14da78d0e98c54e71f85f915ba57e485630ee90675cc7f73", "generation_seconds_batch": 15.647205361980014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3439236879348755, "target_z": -0.15039060037073934, "ce": 6.292664527893066, "genuineness": 4.369274139404297, "identity": 0.6296707391738892, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e3af275d824c1cd7f832c2df354e179b4199792814acbfeef5d243a7c067928e.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "e4142e7e2e6e61f46afd5b368016e9fbac7955c701b0b2145d12cc9d3740b2a2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f2c630671bd336922989ef2b0a94a47dd8714fb34e625c7d0a41089ecb59991e", "generation_seconds_batch": 23.33231629501097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0581735372543335, "target_z": 0.84374997925957, "ce": 5.7684478759765625, "genuineness": 3.6914620399475098, "identity": 0.4993289113044739, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e4142e7e2e6e61f46afd5b368016e9fbac7955c701b0b2145d12cc9d3740b2a2.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "e436fbcc2a46a3e315f3b5e82022cad2a092482611b0e6ab32fbdda6394e8e0c", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ff037df8833e935a94b928e0d36b85cb47cff5c7530914528ad9b9140300eff0", "generation_seconds_batch": 25.967657349887304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209723711013794, "target_z": 1.0546876192574728, "ce": 6.149696350097656, "genuineness": 4.168440818786621, "identity": 0.6680066585540771, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e436fbcc2a46a3e315f3b5e82022cad2a092482611b0e6ab32fbdda6394e8e0c.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "e4c78a02104018530cdb89a9e3ef1d7cf24ead342e499d5035432548de669575", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4ab4c19d85c20ca3b164107ea977768e4775f4451272426c47b46b790b896bd0", "generation_seconds_batch": 22.708817503065802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.634394645690918, "target_z": 0.2539062525925537, "ce": 6.221180438995361, "genuineness": 3.998987913131714, "identity": 0.6849170327186584, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e4c78a02104018530cdb89a9e3ef1d7cf24ead342e499d5035432548de669575.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "e53bd605d44d9952fde55fa443071e5268a462fa50e3127455f32b59cd650199", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d4256aaa86b5230b45ceb7ca8a760e17b04f1d08484b3f1f5c23d6fe16097e15", "generation_seconds_batch": 21.008302862057462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4337311089038849, "target_z": -0.025390641851599404, "ce": 6.173524379730225, "genuineness": 3.9173994064331055, "identity": 0.3302845358848572, "hypothesis": "The 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_Elation/e53bd605d44d9952fde55fa443071e5268a462fa50e3127455f32b59cd650199.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "e5612eec492494edc9ca5b229b1190025aa36c4b8167196d5cbbe34f6a32e451", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3db1e305b91ef727808f219ed97ce138666728b8cf67d53163c88b5e971c6a01", "generation_seconds_batch": 16.97691905288957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2583259344100952, "target_z": -0.26953126296276875, "ce": 6.006728172302246, "genuineness": 4.20609712600708, "identity": 0.6231440901756287, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e5612eec492494edc9ca5b229b1190025aa36c4b8167196d5cbbe34f6a32e451.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "e5c0dff31fd133585ce1b853579a5fb49f86c885f3d8a09691930a0769dd7e23", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e90b024fccb61c5cd13ca5df72d723c64a7bdcb914a2f798dc9cab7283a14c74", "generation_seconds_batch": 22.234008386032656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2709551155567169, "target_z": -0.25195312629627686, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.4639984369277954, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e5c0dff31fd133585ce1b853579a5fb49f86c885f3d8a09691930a0769dd7e23.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "e62938a8978c69db41ac60314068b1b37775d4ee895cd9a452c4cdc9dcfc0a95", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "32312f78941850610c23e82279bed29e71120e2353ff0524180455ba98d6f5d0", "generation_seconds_batch": 17.64776532794349, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.068507432937622, "target_z": 2.25000008296172, "ce": 6.38003396987915, "genuineness": 4.394378662109375, "identity": 0.3907913267612457, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e62938a8978c69db41ac60314068b1b37775d4ee895cd9a452c4cdc9dcfc0a95.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": "e6b4099e9eb8729e820853584b7ad9e005b0d1188df5024dc30b65a9a3b6959c", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a9be08ef00945bde30cb56ca1c5a43b7f8d6661a334d4248524eb874a2e6b67", "generation_seconds_batch": 22.946684169000946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4454681873321533, "target_z": 1.3828125051851075, "ce": 5.967014789581299, "genuineness": 4.162164688110352, "identity": 0.6378847360610962, "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_Elation/e6b4099e9eb8729e820853584b7ad9e005b0d1188df5024dc30b65a9a3b6959c.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "d4f4b322cd46ecb545d45c7600f10bb3511bde1e546009a903d066e6f640b81c", "generation_seconds_batch": 17.380560722085647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03100082278251648, "target_z": -0.5859375155553225, "ce": 6.483288764953613, "genuineness": 4.570107460021973, "identity": 0.3440406322479248, "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_Elation/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "e735490ee7e2c548040f8f2d9141ca0714cfed783f861e490ce0997b3fe79087", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1f6ab264e715ef26032ba0f36c332fb08b705dd4c82f7ec50cf92e4d9c0fb4d3", "generation_seconds_batch": 15.495586931006983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8645262718200684, "target_z": 0.5742187992585214, "ce": 6.078212261199951, "genuineness": 3.973883628845215, "identity": 0.5175068378448486, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e735490ee7e2c548040f8f2d9141ca0714cfed783f861e490ce0997b3fe79087.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "e76a42c568d3279b3f62793e567fc1843c208aebb8ca90c965cca8bd4af941e0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d2b967d04c7cc31a2f75128b60988be2d253972771914d6ac580d92891c192f1", "generation_seconds_batch": 16.976909947930835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0553669929504395, "target_z": 0.8398436437052961, "ce": 5.919358730316162, "genuineness": 3.948779582977295, "identity": 0.4143874943256378, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e76a42c568d3279b3f62793e567fc1843c208aebb8ca90c965cca8bd4af941e0.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "e77a1c65ad8f24a2f71aa7af162baaaa8ea1a953ce818d864c028889b2401228", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "12a10cf442586a69606ebf17035933532f2a19368a263faadb82866fef4c1ad0", "generation_seconds_batch": 24.679392969002947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9562480449676514, "target_z": 2.09374997925957, "ce": 5.514282703399658, "genuineness": 3.603597402572632, "identity": 0.18806535005569458, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e77a1c65ad8f24a2f71aa7af162baaaa8ea1a953ce818d864c028889b2401228.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "e7afb2fc4797d6810cca1d59da04d96c4b220b9cda975a694ca7ef22a2652a3e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "184839fa97ea8927c17c840f4c2a2ded74687317159d9778893258ef4d1761f3", "generation_seconds_batch": 22.033067221054807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4380710124969482, "target_z": 4.15625002074043, "ce": 5.748591423034668, "genuineness": 3.7918784618377686, "identity": 0.590996265411377, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e7afb2fc4797d6810cca1d59da04d96c4b220b9cda975a694ca7ef22a2652a3e.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "e7e35a0682675198a6d7641dc243e2bdfb78c3967bc17660e622c87cb36ac9a1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c541f7d5102b934d2f0e4b6c1b231fe886e743c8d07408868bb0290b0b55030", "generation_seconds_batch": 22.954179021995515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8271498680114746, "target_z": 1.9140625259255375, "ce": 6.292664527893066, "genuineness": 3.9173994064331055, "identity": 0.22107450664043427, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e7e35a0682675198a6d7641dc243e2bdfb78c3967bc17660e622c87cb36ac9a1.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": "e880598c2a3f27b32fb4bd4b2319e50d2297138c1512f9938b30a9d584ba2444", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Your message arrived after I had left.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41fc9f5076a5e739a872e3c07689bcebfe22efd32cec87216cc2053232308042", "generation_seconds_batch": 23.373896717093885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18956711888313293, "target_z": -0.3652343685186156, "ce": 6.435632705688477, "genuineness": 4.218649387359619, "identity": 0.3664921522140503, "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_Elation/e880598c2a3f27b32fb4bd4b2319e50d2297138c1512f9938b30a9d584ba2444.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "e889d87fca227b8736ef0b68ba82f84e7ba25babaccf606b5726fbc295a501ff", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9168534b3e39258aed612549f15473e87f4ee5b21d276d8213f1a777bffe968f", "generation_seconds_batch": 17.02493359800428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.900118350982666, "target_z": 2.0156249274084947, "ce": 5.744620323181152, "genuineness": 3.9425034523010254, "identity": 0.5300059914588928, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás abierto.", "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_Elation/e889d87fca227b8736ef0b68ba82f84e7ba25babaccf606b5726fbc295a501ff.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "e8cb3216c032fc45db558669b6782f6c28e1946d14f84b002a261a9b8a4d7c89", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e73247826a9d6d9c804fa3cfbb1df6d3f30a0c70031daa67f986ce64ac478d2", "generation_seconds_batch": 16.260606224066578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.035721778869629, "target_z": 0.8125001244425802, "ce": 5.522225379943848, "genuineness": 3.6663577556610107, "identity": 0.4731154441833496, "hypothesis": "The 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_Elation/e8cb3216c032fc45db558669b6782f6c28e1946d14f84b002a261a9b8a4d7c89.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": "e8f5f14829d17eb9c58e934b11abe8c8740af185adaf53e3908cea3f450d0e28", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f24abc758cbcdb809c9c350fcbb7e4e78e1964ccfcb7bbf0f458f8e46dbce7a5", "generation_seconds_batch": 16.86192427703645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32568153738975525, "target_z": -0.17578124222233873, "ce": 6.205295085906982, "genuineness": 4.557555198669434, "identity": 0.5822891592979431, "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_Elation/e8f5f14829d17eb9c58e934b11abe8c8740af185adaf53e3908cea3f450d0e28.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": "e8ff3d6216afcc38ac5a6758c800a88b846263bee508fb820059d7919cccb64c", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c75f83ab24799e10c8b010d6ca579b65870f9848c8d8d65fce0ff6d205cb37c", "generation_seconds_batch": 16.267872247030027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40847277641296387, "target_z": -0.06054687370372312, "ce": 6.372091293334961, "genuineness": 4.632867813110352, "identity": 0.720321774482727, "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_Elation/e8ff3d6216afcc38ac5a6758c800a88b846263bee508fb820059d7919cccb64c.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "e92aae9782963d15903ec8fe479a9e26a827e5b9296db0f2aafb25b5472dcc3f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6ed647700717c490998b098ce2296f5be45d3d7a0e66e4503e2067b3bb8ce070", "generation_seconds_batch": 21.50097350194119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2826921939849854, "target_z": 1.15625002074043, "ce": 5.919358730316162, "genuineness": 4.162164688110352, "identity": 0.5625355839729309, "hypothesis": "Die Tür 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_Elation/e92aae9782963d15903ec8fe479a9e26a827e5b9296db0f2aafb25b5472dcc3f.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "e92bf0a8a286cdfe281f8d0e5114faff7c30c7c6281f3f3a6f3d1152a7ebe342", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f47cee9787054c011fccea1536febbe949ff11063f5aed4bd73b642cdc74c0ce", "generation_seconds_batch": 23.059506459976546, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7541813850402832, "target_z": 1.8125001244425802, "ce": 5.990842819213867, "genuineness": 3.986435890197754, "identity": 0.5392426252365112, "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_Elation/e92bf0a8a286cdfe281f8d0e5114faff7c30c7c6281f3f3a6f3d1152a7ebe342.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "e9447b37636c29481298e7aaf720ce9007ff24c9a7ecaf77acd643f7db5ef561", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4584f92095667ef8df960c2351a677bf3cd6e01005598279d45d708664f55a7c", "generation_seconds_batch": 23.412201669998467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6522557735443115, "target_z": 3.06249995851914, "ce": 5.808161735534668, "genuineness": 3.9550557136535645, "identity": 0.33700454235076904, "hypothesis": "¡Encontra la cajita! Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro de la casa.", "wer": 0.29411764705882354, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e9447b37636c29481298e7aaf720ce9007ff24c9a7ecaf77acd643f7db5ef561.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "e9a473b10335023ba76c83340776ab92a1e1f03d368fdaccf5fe71e15046c305", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b4fa34cd7701215d7c6f67609a226d549c2d06e7a8e24daaad871a15f160aaa", "generation_seconds_batch": 22.727706743986346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7869670391082764, "target_z": 3.25000008296172, "ce": 5.522225379943848, "genuineness": 3.785602569580078, "identity": 0.5037646293640137, "hypothesis": "¡La puerta sigue abierta! He dejado tu abrigo sobre la silla. Dime cuándo estás lindo.", "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_Elation/e9a473b10335023ba76c83340776ab92a1e1f03d368fdaccf5fe71e15046c305.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "8c070f06cbf436898395ad3b8f2fb5fb95087fab842f16fbc79362378405666c", "generation_seconds_batch": 17.241437104996294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15308284759521484, "target_z": -0.41601561074095433, "ce": 6.395919322967529, "genuineness": 4.406930446624756, "identity": 0.6313905119895935, "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_Elation/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "e9d501ae9d1e803e2d2771f28284ef8a593f51c3bedfb35f2f0e4c884220aba1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65d2bfad2ecabe9800766e050a2bdd2574a8aa4dda2a7d7cf1efc71b6d92b563", "generation_seconds_batch": 15.474798048031516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8383758068084717, "target_z": 1.9296875362957526, "ce": 5.95112943649292, "genuineness": 3.9425034523010254, "identity": 0.634904146194458, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/e9d501ae9d1e803e2d2771f28284ef8a593f51c3bedfb35f2f0e4c884220aba1.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": "ea177012568dc0311b7f4a9d561fbbc8a40fb4866e7a076899ae19edd209cb78", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3f2acaa3b61d7e61c6ea38b9fe4be145af0c77197f4dee9d0f945472e708894b", "generation_seconds_batch": 23.28350764804054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2714662551879883, "target_z": 1.140625010370215, "ce": 6.221180438995361, "genuineness": 4.231201171875, "identity": 0.6962153911590576, "hypothesis": "The route turned a gauche up the pont. Continue jusqu'a petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.35, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ea177012568dc0311b7f4a9d561fbbc8a40fb4866e7a076899ae19edd209cb78.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "eaaa76eec297fb082b66cf1bee1002c4d5514cec508092192db5914e2437c3e2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "75258ea059b9252ba323f02afe16d7a1dcc449297c58dc2ca7062a0bd6235d56", "generation_seconds_batch": 23.916111625963822, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5558131337165833, "target_z": 0.14453126296276878, "ce": 5.911416053771973, "genuineness": 3.5220088958740234, "identity": 0.3616969883441925, "hypothesis": "The 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_Elation/eaaa76eec297fb082b66cf1bee1002c4d5514cec508092192db5914e2437c3e2.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": "eb1584d435d4fbe5dc4b883886ecdcffcc79868b2481dd3a7a5a196688e09ba4", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Escribí el número en el sobre.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24728b61263702feedf88e64928b5bac2dd8e544e00d122ece764b61374d67fe", "generation_seconds_batch": 15.742755199084058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7129761576652527, "target_z": 0.36328124222233876, "ce": 6.316492557525635, "genuineness": 4.13078498840332, "identity": 0.6053758859634399, "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_Elation/eb1584d435d4fbe5dc4b883886ecdcffcc79868b2481dd3a7a5a196688e09ba4.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "eb1ac8e4d12545b6b24710211bfe03b1c2124b9d1a55b9d6e0b45e8cb8f807e1", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9325c906231ddab103ad12604f21bcf9de9afbe7553592600552c6b1eeeeebc9", "generation_seconds_batch": 22.39607007394079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8953975439071655, "target_z": 0.6171874948148925, "ce": 5.919358730316162, "genuineness": 3.5220088958740234, "identity": 0.4224206805229187, "hypothesis": "Ik 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_Elation/eb1ac8e4d12545b6b24710211bfe03b1c2124b9d1a55b9d6e0b45e8cb8f807e1.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "eb28da01bd05716fd4f9dc1a129167546a68596eea647b27125defee85e709f6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b9d2cca216fe9b2da1e7a749003714cae0b2387a197d8d33e143fe1938d45d14", "generation_seconds_batch": 22.54204666498117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4230163097381592, "target_z": 1.3515624844446774, "ce": 5.7406487464904785, "genuineness": 3.8546390533447266, "identity": 0.2487424612045288, "hypothesis": "De deur 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_Elation/eb28da01bd05716fd4f9dc1a129167546a68596eea647b27125defee85e709f6.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "eb4b6d471a10fec91f26622b37d9682e2d1d0616d35d9962df01c33d3954f514", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "16a40e45b492d4e16c73bf11b8e9626d4ade39d6597a042893a2b4a95379d342", "generation_seconds_batch": 25.264440363971516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9337961673736572, "target_z": 2.06249995851914, "ce": 5.677107334136963, "genuineness": 3.5973212718963623, "identity": 0.6875339150428772, "hypothesis": "The 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_Elation/eb4b6d471a10fec91f26622b37d9682e2d1d0616d35d9962df01c33d3954f514.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "eb4cfaa4af71ec5e5a39394da4b8507a988457fb97164f195892757dc9aa59a7", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "01d17ac586edc1df1e20d876cd5b5cbadc5d584c623eb10b9bc49e1ce7998a65", "generation_seconds_batch": 25.005733322002925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5614261031150818, "target_z": 0.15234376814787629, "ce": 5.959072113037109, "genuineness": 4.306513786315918, "identity": 0.6384420990943909, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/eb4cfaa4af71ec5e5a39394da4b8507a988457fb97164f195892757dc9aa59a7.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "ebc48725ab3c4548033d37ecd841e108dc16ab5bd409749c4974cfc6afc138ca", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fd1408a017b1d34674171a85c25b4d18c2b65f89de825e4fa07c677e2a09c5a1", "generation_seconds_batch": 16.019124439102598, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6185779571533203, "target_z": 3.0156249274084947, "ce": 6.340320587158203, "genuineness": 3.8671910762786865, "identity": 0.43170544505119324, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ebc48725ab3c4548033d37ecd841e108dc16ab5bd409749c4974cfc6afc138ca.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": "ebcea608e9017670a673c36487cb6ccc18b7bffea7384af2806d9340a427613e", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Your message arrived after I had left.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cbe595fd9b870eea67ef497e30521e677054a81160da2502ed4c3e34b7c274b", "generation_seconds_batch": 18.434494646964595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.604926586151123, "target_z": 0.2128906418515994, "ce": 6.348263263702393, "genuineness": 4.20609712600708, "identity": 0.4160630702972412, "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_Elation/ebcea608e9017670a673c36487cb6ccc18b7bffea7384af2806d9340a427613e.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "ed377e461185b93f5c7bfb9b9dec432cd9dac04c5c628fd31e68a08e662c256c", "generation_seconds_batch": 17.207649796968326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16992172598838806, "target_z": -0.3925781366664919, "ce": 6.181467056274414, "genuineness": 4.337893962860107, "identity": 0.8057236075401306, "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_Elation/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "ec097afc4f29965047511b4caac7f379c1e77d146355bcf1a985dab486dfef78", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5218439dfea994cf2ad735664bae060bbf60744281828aa5e3cca9dfcd628d8b", "generation_seconds_batch": 23.24921011494007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4189970791339874, "target_z": -0.04589844722207658, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.7332369089126587, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ec097afc4f29965047511b4caac7f379c1e77d146355bcf1a985dab486dfef78.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "ec0ed2ea2877a102687dfb9ebe25d2dcea0bce4ebb9faac120e9064d5f97f011", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "954e321d0ec29543e7e006fbdad3bb4890980a68cf9aac9ced7f1f3e15a43c5e", "generation_seconds_batch": 22.461153862066567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.521082878112793, "target_z": 0.09619137675970105, "ce": 6.173524379730225, "genuineness": 4.231201171875, "identity": 0.5793123245239258, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ec0ed2ea2877a102687dfb9ebe25d2dcea0bce4ebb9faac120e9064d5f97f011.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "ec1e404d2db14e7bd669f0ca9da572fde09b74dab3a455fd84c0a13e6341c037", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "06b39401b11bb1d348a48d2c3a09f339eaad1bc3ce8c7d8c05880f94627c4307", "generation_seconds_batch": 21.78701174107846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6868257522583008, "target_z": 1.7187500622212901, "ce": 6.284721851348877, "genuineness": 4.036643981933594, "identity": 0.27369898557662964, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ec1e404d2db14e7bd669f0ca9da572fde09b74dab3a455fd84c0a13e6341c037.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "ec271612fb416ebf8e9041ff79a1bb00c9dbc98f8a41b0cb1df436bffa209f76", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "126dd53f33aff799a0c46469b30061496595715e5511a923147c8d27111dc21f", "generation_seconds_batch": 23.072556155035272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19097036123275757, "target_z": -0.36328124222233876, "ce": 6.260893821716309, "genuineness": 4.507347106933594, "identity": 0.6448980569839478, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ec271612fb416ebf8e9041ff79a1bb00c9dbc98f8a41b0cb1df436bffa209f76.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "ec2741828ad88bae2f828ee91133e0db0780b8c4b3e2be95a67d257a3cd608c8", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7794b24ef30689bdb291a03217147d6a4d7286d5b0ccd4724ed28a5257c7890d", "generation_seconds_batch": 22.959017605986446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.727008581161499, "target_z": 0.3828125051851075, "ce": 5.982900142669678, "genuineness": 4.243753433227539, "identity": 0.691903829574585, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ec2741828ad88bae2f828ee91133e0db0780b8c4b3e2be95a67d257a3cd608c8.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "ec5a2e58e9b6e724e836c45f5de6fe3fcc74fbdd4cfd2948d54129274f200fa6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4d8f802b5b2b14976891f2eaf3dbdcb8716c58f77963e7b3cac7d5798fccfd0d", "generation_seconds_batch": 15.85167281597387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9890336990356445, "target_z": 3.53124993777871, "ce": 5.959072113037109, "genuineness": 3.9048471450805664, "identity": 0.5755789279937744, "hypothesis": "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_Elation/ec5a2e58e9b6e724e836c45f5de6fe3fcc74fbdd4cfd2948d54129274f200fa6.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": "ec680089317b49983506ef465af6f445f225cd4dac984b6188a881c08f33cce7", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e7d34944c15005a8af1acb9be9b37987790d03726ee36f8c894a67e2ec875f2", "generation_seconds_batch": 15.24906518298667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0104633569717407, "target_z": 0.7773437681478763, "ce": 6.117925643920898, "genuineness": 3.810706615447998, "identity": 0.5018355846405029, "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_Elation/ec680089317b49983506ef465af6f445f225cd4dac984b6188a881c08f33cce7.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "ec6a60c5d0dd3d7e19caf0ed19c515e723d3391fc1b5972f9dd5ba4d622491f0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d10a2789bf21a61b37451442af0a4207daa6e53375b15de08dfd7692fa16b58c", "generation_seconds_batch": 22.907866170979105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0609800815582275, "target_z": 0.8476563148138438, "ce": 5.728734970092773, "genuineness": 4.017816066741943, "identity": 0.3453371226787567, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ec6a60c5d0dd3d7e19caf0ed19c515e723d3391fc1b5972f9dd5ba4d622491f0.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "ece6f761c773798579bae1242fda4f2e14633f39383d63740990a4d5c4511710", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1835a069ccc6ea495e8a25db1516b0692bb19ad276ec125982235495edc8b3f9", "generation_seconds_batch": 23.031228719977662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5914053916931152, "target_z": 1.5859376399979028, "ce": 6.046441555023193, "genuineness": 4.337893962860107, "identity": 0.34246110916137695, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ece6f761c773798579bae1242fda4f2e14633f39383d63740990a4d5c4511710.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "ed502caf039a2b72374b51a826f5d1e2dfff4070a90fc715f5ea1583813b978f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1fdeee1a786435667bd90feac4329c97f502a09cdfe712be3945b8b9b215ad91", "generation_seconds_batch": 21.959386009024456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3768998384475708, "target_z": -0.10449219462952282, "ce": 5.808161735534668, "genuineness": 3.860914945602417, "identity": 0.4484092593193054, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás linda.", "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_Elation/ed502caf039a2b72374b51a826f5d1e2dfff4070a90fc715f5ea1583813b978f.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": "edcead5fd8315969c77fadb4265a89fcce4d25b5ea7a7f618f37133ead8f166a", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a6929274b5de1bc82bb6492426ef926cda054d96064b3863b1d865e64e49c18", "generation_seconds_batch": 16.760362180997618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5523050427436829, "target_z": 0.1396484679625066, "ce": 6.316492557525635, "genuineness": 4.231201171875, "identity": 0.616832971572876, "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_Elation/edcead5fd8315969c77fadb4265a89fcce4d25b5ea7a7f618f37133ead8f166a.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": "edfc64555ba06dfaafe18aa7a5fb710d12e013c12b4f36cb8f9cc37b48aa5812", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a423cfaddbcf333e1a7cedbc113ee0100d73577153d34a7d3e29943a4cfd129", "generation_seconds_batch": 16.760362180997618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.237788438796997, "target_z": 1.09374997925957, "ce": 6.475345611572266, "genuineness": 4.381826400756836, "identity": 0.5335235595703125, "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_Elation/edfc64555ba06dfaafe18aa7a5fb710d12e013c12b4f36cb8f9cc37b48aa5812.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": "ee003768b1bb90c1019a44735451efb9f70ba1b780cb6122fad986f38ed64f19", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0255ad27d53fa6c48997bce8b0583374b90144ba73640f22886e5024f3afbe11", "generation_seconds_batch": 21.401879413053393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9038169980049133, "target_z": 0.6289062525925537, "ce": 6.117925643920898, "genuineness": 4.268857479095459, "identity": 0.5972366333007812, "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_Elation/ee003768b1bb90c1019a44735451efb9f70ba1b780cb6122fad986f38ed64f19.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "ee5c7aac9499c6db03eb0f724fb7ff0bb03ac2b678e4f825d6ca26fa33b7ad2f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "49b3b9df9c8b5cf22659031071b75f8bdbd905e5ccb7d70488dc287a2d138b34", "generation_seconds_batch": 24.11119312106166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7031534910202026, "target_z": 0.3496093996292607, "ce": 6.435632705688477, "genuineness": 4.105680465698242, "identity": 0.5460109114646912, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ee5c7aac9499c6db03eb0f724fb7ff0bb03ac2b678e4f825d6ca26fa33b7ad2f.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "eeb58fa6303163056c5d0058b17f385623e95ecc2e419f10ead2be526cc152c5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bd18c7ee269d0561c465782bef8a4238908af2aacc08c09914e6f99839e67adf", "generation_seconds_batch": 24.378707362920977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8448808193206787, "target_z": 0.5468749481489249, "ce": 5.998785495758057, "genuineness": 3.8169827461242676, "identity": 0.5878340005874634, "hypothesis": "De deur staat nog open. De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.2631578947368421, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/eeb58fa6303163056c5d0058b17f385623e95ecc2e419f10ead2be526cc152c5.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "eebe4ad4edeb6ec12ec2a73bb2f8fff12c19776e43f44447d1647a24fd7f94d4", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "6fa73b7eb56f6ef73b944c01c4d462b7dc8290f95d0d4fee0468fd8be35a13d6", "generation_seconds_batch": 22.781430372036994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.742063283920288, "target_z": 3.18750004148086, "ce": 5.240260601043701, "genuineness": 3.798154592514038, "identity": 0.5613510608673096, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás luciendo.", "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_Elation/eebe4ad4edeb6ec12ec2a73bb2f8fff12c19776e43f44447d1647a24fd7f94d4.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "ef88908ec480393ac2cbb64327235b661cb9d11085896071927b0a77f7ef045a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c591b40a59b2a542ddffdaa2ade7e3ced54080c42c5d62095c862560c77260be", "generation_seconds_batch": 20.71985728002619, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8841716051101685, "target_z": 0.6015624844446775, "ce": 6.252951145172119, "genuineness": 4.482243061065674, "identity": 0.6234300136566162, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ef88908ec480393ac2cbb64327235b661cb9d11085896071927b0a77f7ef045a.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "efc3bdc06260a90dc8f2980eb68bc2513bd50279a1597b0bbadd7247f4d13765", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "288c935c2a320aa5b0c88d81b1ad744b7ab4c04f23adf4abf441dad2699f1483", "generation_seconds_batch": 17.108104030019604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27586644887924194, "target_z": -0.24511720499973785, "ce": 6.078212261199951, "genuineness": 4.005263805389404, "identity": 0.34528276324272156, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/efc3bdc06260a90dc8f2980eb68bc2513bd50279a1597b0bbadd7247f4d13765.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "f011464c7badca1b85b74987aa755601bd19b0d55472f372589110dab264fd82", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "647879405d89dc019ae06908bc965b4bd536aace4fe7b5387ff7837177fd4fe7", "generation_seconds_batch": 22.974442468956113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6531479358673096, "target_z": 1.671875031110645, "ce": 6.24500846862793, "genuineness": 4.20609712600708, "identity": 0.6748664975166321, "hypothesis": "J'ai trouvé la 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_Elation/f011464c7badca1b85b74987aa755601bd19b0d55472f372589110dab264fd82.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "f01480f0162998bb70e3be3141cf00243a84d2481cbad041dcf9a5fc1d9c3c34", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0eed525dd1331a1f57987517fd982907d1cbb36391b6d5076bdfdadcc6addec8", "generation_seconds_batch": 16.975781638058834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7340247631072998, "target_z": 0.3925780951856318, "ce": 6.2767791748046875, "genuineness": 4.344170093536377, "identity": 0.6395244598388672, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f01480f0162998bb70e3be3141cf00243a84d2481cbad041dcf9a5fc1d9c3c34.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "f027cc3e227e7f8cc11ba6090ac54285849d85ae6a87a5b73eb7124379e70473", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4cfbc1e5f2193aa86c9832f491bbff79e58a7db48da40dbfc64f832fe23f878c", "generation_seconds_batch": 26.369793663965538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0227115154266357, "target_z": 3.578124968889355, "ce": 5.982900142669678, "genuineness": 3.8169827461242676, "identity": 0.4736107885837555, "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_Elation/f027cc3e227e7f8cc11ba6090ac54285849d85ae6a87a5b73eb7124379e70473.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "f036d3ec0538592473ad014989c8a8bcd83a182e321dfab75557abceca16b10e", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ac1dd8f816aa7747dfd18398b4d2616ff1479643ab1bd0e453f21cb83d30c628", "generation_seconds_batch": 21.71195268095471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1695406436920166, "target_z": 2.3906248444467746, "ce": 5.879645347595215, "genuineness": 4.18099308013916, "identity": 0.5240598917007446, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f036d3ec0538592473ad014989c8a8bcd83a182e321dfab75557abceca16b10e.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "f050365d02e835b365a1ab6e003b3744f57b96e996dcaa6976e06fd1424e1957", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af3b68452fa1f5d898c283245e9adf35f0fe40c8897aba36cb0887a84d67ef4b", "generation_seconds_batch": 21.96396826801356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3258116245269775, "target_z": 3.99999991703828, "ce": 5.728734970092773, "genuineness": 3.9550557136535645, "identity": 0.28300732374191284, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay de aquí.", "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_Elation/f050365d02e835b365a1ab6e003b3744f57b96e996dcaa6976e06fd1424e1957.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "f0b221129474589e18c82b4cfee0426c3e7a12151b601f476e8c6cf29ac9acd5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9361e4e3c8b4e2952e85939ac79b2362827b688f27db11ae53e2416b4e1f5e0c", "generation_seconds_batch": 22.96093306108378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3607625663280487, "target_z": -0.12695312629627686, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.5785436630249023, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f0b221129474589e18c82b4cfee0426c3e7a12151b601f476e8c6cf29ac9acd5.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": "f0d0f2d8c63b56927bfff0622b8ec9b80e74a038cfbb9eeb7dc177650c2028a3", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5272fc04ed323fe2da53e010e868007b699bede4dc6596c50de9ba7edfe1b1dc", "generation_seconds_batch": 22.210163590032607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6194701194763184, "target_z": 1.625, "ce": 6.348263263702393, "genuineness": 4.15588903427124, "identity": 0.6159235239028931, "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_Elation/f0d0f2d8c63b56927bfff0622b8ec9b80e74a038cfbb9eeb7dc177650c2028a3.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "f11ebd5a5d3b492fadc3dae62a1e380e30acdc00d3799996fef40ad1dff29b8f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "86d35f63a45a09e08add2a824b266414c8dbe6bb524ce7360dd6a404eccf423c", "generation_seconds_batch": 21.238748879986815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1114966869354248, "target_z": 0.9179686955563712, "ce": 6.109982967376709, "genuineness": 4.005263805389404, "identity": 0.5850452184677124, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f11ebd5a5d3b492fadc3dae62a1e380e30acdc00d3799996fef40ad1dff29b8f.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "f14694259a5a3a98dae811de6a174bcfcd13bc2bbda3a076526116242338a1c6", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d0fbd0f42f0cc54110120cb4089b1d177158bd8f2e4f02c8044d1ea874770562", "generation_seconds_batch": 23.70061270997394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.248122215270996, "target_z": 2.49999991703828, "ce": 5.585766792297363, "genuineness": 3.6287014484405518, "identity": 0.189360573887825, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f14694259a5a3a98dae811de6a174bcfcd13bc2bbda3a076526116242338a1c6.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": "f1ea13270fea8ed537590a9c580fe3c2881d75759ec4c116804fd0dd448bb6e8", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c8aaa4c0766f7cb477fcf9d1efe911fe39074aee2220dc5bde88cb39d988e50", "generation_seconds_batch": 23.443660684977658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6182574033737183, "target_z": 0.23144536240665978, "ce": 6.157639026641846, "genuineness": 4.017816066741943, "identity": 0.5652313232421875, "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_Elation/f1ea13270fea8ed537590a9c580fe3c2881d75759ec4c116804fd0dd448bb6e8.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": "f200d492e2fff4c3184053006177f53c7aa085e758353917a3ea7e8c67d8b8bf", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The road turns left behind the bridge.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78d4d5d28a5fd85739f6cab96be64baf528a14c82531fc7126f7ed79a0c215e0", "generation_seconds_batch": 22.56849841400981, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14606663584709167, "target_z": -0.42578124222233876, "ce": 6.340320587158203, "genuineness": 4.149612903594971, "identity": 0.47032633423805237, "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_Elation/f200d492e2fff4c3184053006177f53c7aa085e758353917a3ea7e8c67d8b8bf.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "e22914722b3e700d68367b8fc512008f66060939e556fb932ef456e4ac03f67c", "generation_seconds_batch": 16.906058504944667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10537263751029968, "target_z": -0.4824218633335081, "ce": 6.181467056274414, "genuineness": 4.331617832183838, "identity": 0.5960264205932617, "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_Elation/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "f21f93619ef47458bba36b75394807a70d5e2f61ea655ad7d22e46d5bdc30711", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1b42356aaed4e36bfe40e84fc5d5fd06beadc383bd093ddd5f463e54fd09acfc", "generation_seconds_batch": 22.4176809390774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0385282039642334, "target_z": 0.8164062940734138, "ce": 5.808161735534668, "genuineness": 3.8044304847717285, "identity": 0.6557841300964355, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f21f93619ef47458bba36b75394807a70d5e2f61ea655ad7d22e46d5bdc30711.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": "f24d575b8b0e5fb5488b298282989f7fc0b76a0ba2bcbbf8702ac60f0091ff82", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Someone moved the little blue chair.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "843a8663f3e06808aac47ed3d60f3a8d2b25f194b1b0a21296d98e067278f17e", "generation_seconds_batch": 20.33409830799792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1348406970500946, "target_z": -0.4414062525925537, "ce": 6.395919322967529, "genuineness": 4.432034492492676, "identity": 0.5178261399269104, "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_Elation/f24d575b8b0e5fb5488b298282989f7fc0b76a0ba2bcbbf8702ac60f0091ff82.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "f259ac850dee300b836e73ec48a329ab0d21173496e29f7179cb4d4c57ec5871", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bf53a58dc5b7a2b56af24c2886b0710c6c41e0896b65c3b8d129fb95f9ebc422", "generation_seconds_batch": 24.433581848978065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9225702285766602, "target_z": 2.046874948148925, "ce": 6.356205940246582, "genuineness": 4.105680465698242, "identity": 0.507820188999176, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f259ac850dee300b836e73ec48a329ab0d21173496e29f7179cb4d4c57ec5871.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "f2aab371b5da730f9d3c856d2258dba7279f8bc5384885436a6db5a359ff2d39", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "080d0e3538ddffe5516712d8e0c8d031805bc6406bd06f3c34aba5eb7b3996e1", "generation_seconds_batch": 15.780030117952265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3614642024040222, "target_z": -0.1259765424077084, "ce": 6.340320587158203, "genuineness": 4.243753433227539, "identity": 0.32792097330093384, "hypothesis": "The 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_Elation/f2aab371b5da730f9d3c856d2258dba7279f8bc5384885436a6db5a359ff2d39.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "f2d86a9034a1c0d6be47b0bec3b53a8661f7a98d89e200e6c58b96dcc2cff176", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "db388c1c9a67281a15f33e45b455cf7c98837fe65aef02d7c0909d2878cefe00", "generation_seconds_batch": 21.88113545696251, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1021852493286133, "target_z": 2.2968751140723653, "ce": 5.784333229064941, "genuineness": 3.5690791606903076, "identity": 0.33177804946899414, "hypothesis": "The 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_Elation/f2d86a9034a1c0d6be47b0bec3b53a8661f7a98d89e200e6c58b96dcc2cff176.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "f3766848d86eb49106b412598f5031cee255fb9eb43885cec1a09471185571c2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "571d5e9c4643b0abb7bcf0da948f5bc8914c7c4effc34fed249e228013a268a9", "generation_seconds_batch": 17.33078374399338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.88327956199646, "target_z": 1.9921875777766127, "ce": 5.7247633934021, "genuineness": 3.3870739936828613, "identity": 0.3703579008579254, "hypothesis": "The 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_Elation/f3766848d86eb49106b412598f5031cee255fb9eb43885cec1a09471185571c2.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "f37d0a8e156101876a48094fc25fd6ce3493dc47cf24b5c82d0a9ada54b39943", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5b1f46d50f0fb42c3ffcdec54e03cbb2147774a76c62c5ee13827e215f4099ab", "generation_seconds_batch": 20.339327460038476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3702344298362732, "target_z": -0.11376955490705301, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.548375129699707, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f37d0a8e156101876a48094fc25fd6ce3493dc47cf24b5c82d0a9ada54b39943.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "f3bc6af87f6510391757d938386a193cd19099911d02616354a1d7a3af8773b5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "333f672a6bd6ace6a3fd90baa709712b6d5ab481f8106da8f707dae8d459a380", "generation_seconds_batch": 22.89549993898254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9665818214416504, "target_z": 3.49999991703828, "ce": 5.538110733032227, "genuineness": 3.773050308227539, "identity": 0.3926265239715576, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "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_Elation/f3bc6af87f6510391757d938386a193cd19099911d02616354a1d7a3af8773b5.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "f3e2fa9ea3ade729af03c29a92563954473f6cca285ce3a4fbdaad3e8ca66c60", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2a22063770da74246b1ed3fcc4662a0ab28384dcd378e51d6df9cb0d651c50bb", "generation_seconds_batch": 24.089942379039712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3388218879699707, "target_z": 1.234375072591505, "ce": 5.808161735534668, "genuineness": 3.8797430992126465, "identity": 0.5867549777030945, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f3e2fa9ea3ade729af03c29a92563954473f6cca285ce3a4fbdaad3e8ca66c60.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "f4771c09b56c47f94a1aec86f8f0bd9a3a4aa5db83b6b52188d04872f4ca3962", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9ff9f333d02f669b27378c481b6a9208b4e736fe2643c1fd2de9ff1768eb6368", "generation_seconds_batch": 21.008302862057462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7466539144515991, "target_z": 0.41015619037126366, "ce": 5.9431867599487305, "genuineness": 3.591045379638672, "identity": 0.2949797809123993, "hypothesis": "The 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_Elation/f4771c09b56c47f94a1aec86f8f0bd9a3a4aa5db83b6b52188d04872f4ca3962.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "f4e9f5e421d5cd8b8bafab854d8bc0f040d78c4316123ecc2784a246f799bf7d", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "83807b07b4b378c82c9d8a862930e12f333b3ed52f3c1fc4af02ff71ebd513d8", "generation_seconds_batch": 17.9664074620232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6210638284683228, "target_z": 0.2353515320374934, "ce": 6.24500846862793, "genuineness": 4.287685871124268, "identity": 0.5822734236717224, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f4e9f5e421d5cd8b8bafab854d8bc0f040d78c4316123ecc2784a246f799bf7d.mp3" }, { "id": "emo_Elation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-0", "key": "f50ca9ad760347deaf6d1e38053afeafc5fab669f0b9978caf5422a52ae3a6b3", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La porte est encore ouverte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "eea4d91efce91c21a89d509975b5cf1897b5b1719236dd1cd84e3240a0cb944b", "generation_seconds_batch": 23.014920226996765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9739790558815002, "target_z": 0.7265624844446775, "ce": 6.062326908111572, "genuineness": 4.049196243286133, "identity": 0.5084169507026672, "hypothesis": "La porte est encore ouverte. J'ai poussé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f50ca9ad760347deaf6d1e38053afeafc5fab669f0b9978caf5422a52ae3a6b3.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "f50fa2d923e4e6894a2c24269a38a0d410195b33fd77db219d14ca50812bfe27", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "67f1c3c9a55a1aee450c6c0cbd6e2951c0839da37231aade2a2013d24d6c781b", "generation_seconds_batch": 23.152569158934057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.427737236022949, "target_z": 2.75000008296172, "ce": 6.173524379730225, "genuineness": 4.13078498840332, "identity": 0.48241299390792847, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f50fa2d923e4e6894a2c24269a38a0d410195b33fd77db219d14ca50812bfe27.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "f587dff50a530908dce9a05b1b893102a3f209f6104f4316f19e9fc54cd25420", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b90515426e951bab30ab44f1eb24d79da3b09e060e1dc350cfcf30f152797eab", "generation_seconds_batch": 21.460230006021447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3051440715789795, "target_z": 1.18750004148086, "ce": 6.268836498260498, "genuineness": 4.005263805389404, "identity": 0.31805694103240967, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f587dff50a530908dce9a05b1b893102a3f209f6104f4316f19e9fc54cd25420.mp3" }, { "id": "emo_Elation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-0", "key": "f61687f7afb11808b508ba44a07ef4114e39dc8292079a00b9aeb360c6183c24", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] La puerta sigue abierta.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7c16d8d06b97b847d00a6c8a8e09971360e200fb2eeee155db5b4d86a09966da", "generation_seconds_batch": 25.09075260499958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9778077602386475, "target_z": 3.5156249274084947, "ce": 5.411027908325195, "genuineness": 3.760498285293579, "identity": 0.2150542289018631, "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_Elation/f61687f7afb11808b508ba44a07ef4114e39dc8292079a00b9aeb360c6183c24.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "f61b75c58267b952f65d70000435b5981af6f0817db6ecc3db0db6250fcc4710", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "894f8b785a62fc3be5fae9a804e2093bc89d32bfa4886e3dd464d9af0c3fbe6d", "generation_seconds_batch": 22.453645478002727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6747076511383057, "target_z": 3.09374997925957, "ce": 5.772419452667236, "genuineness": 3.898571252822876, "identity": 0.388130784034729, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f61b75c58267b952f65d70000435b5981af6f0817db6ecc3db0db6250fcc4710.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "f61fa42edc3b5cc40e5ce40fa7c983338aade92a26bcf5155d7d8b5ba0312097", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1bc75a525a900fc204d951d22cb127d342693bd2b0ab62ae5957151ebb9b6756", "generation_seconds_batch": 23.04711867601145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5379217863082886, "target_z": 0.11962889231502358, "ce": 6.125868320465088, "genuineness": 3.886019229888916, "identity": 0.30341655015945435, "hypothesis": "The 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_Elation/f61fa42edc3b5cc40e5ce40fa7c983338aade92a26bcf5155d7d8b5ba0312097.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "f6aaf0fa8c9e0c71f892bb743ead3f1182c4a174944a65cf712867964c1091ae", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "20db59c59f3e18da0b71b50d5de3f75bdbf57eb98308f130856406bdfec08086", "generation_seconds_batch": 23.152569158934057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.236896276473999, "target_z": 2.484374906668065, "ce": 6.046441555023193, "genuineness": 4.080576419830322, "identity": 0.40224093198776245, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f6aaf0fa8c9e0c71f892bb743ead3f1182c4a174944a65cf712867964c1091ae.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "f73121f03bb9c748873092af4a7a0664e05074b54a9dcccaebb5ca34a4144475", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0dac533202d33bfe1b5cc40b0bb301c405f7b935437e3b7e591339f94df96244", "generation_seconds_batch": 22.97725818201434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9010105133056641, "target_z": 0.625, "ce": 6.24500846862793, "genuineness": 4.243753433227539, "identity": 0.47758492827415466, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f73121f03bb9c748873092af4a7a0664e05074b54a9dcccaebb5ca34a4144475.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": "f79d837f8ff8adbab5300107c5286a1a58b9ddf1eb0edf840b3f96507f36b2f5", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3b21b3d1692b9d23e3a9685861f010663bb7b42229a41b4f7c2b2ebd820e6406", "generation_seconds_batch": 15.202546224929392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2714662551879883, "target_z": 1.140625010370215, "ce": 5.974957466125488, "genuineness": 3.9425034523010254, "identity": 0.5942115783691406, "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_Elation/f79d837f8ff8adbab5300107c5286a1a58b9ddf1eb0edf840b3f96507f36b2f5.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "b6ce66922a62d9e5106b9d8bcfebfdde81f46c28a622352529ddb393e87c03cb", "generation_seconds_batch": 18.686592967016622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028194338083267212, "target_z": -0.5898437681478763, "ce": 6.141753673553467, "genuineness": 4.7081804275512695, "identity": 0.6311670541763306, "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_Elation/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.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": "f85dbd80e89248c1050c6363b4ffdb92e665116137797ccb9ad3f5f741fc21b4", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [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": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0a20a0ebefca7c2b00e7a77d8ea3e38a4dd74a7d2af4e91cba00a1f78a2f37e0", "generation_seconds_batch": 24.940343503956683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8280419707298279, "target_z": 0.5234375155553225, "ce": 6.419747352600098, "genuineness": 4.268857479095459, "identity": 0.5202087163925171, "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_Elation/f85dbd80e89248c1050c6363b4ffdb92e665116137797ccb9ad3f5f741fc21b4.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_Elation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": "5b78c496fbbfc07f79c6bfb914c557f74bced1dfb4429b55437d55051d70539a", "generation_seconds_batch": 18.41770422994159, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10116291046142578, "target_z": -0.48828124222233876, "ce": 6.284721851348877, "genuineness": 4.6203155517578125, "identity": 0.6692257523536682, "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_Elation/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "f8b7dac84e22fe936460018f7b3832a9d0846b4f2bbc7bb3d9c1edf2dee207ec", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7068a211c1a007c8dca1a07da07b6666a3428c4ed4190af6bb9ce230beb7d7ce", "generation_seconds_batch": 23.25605090300087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6989437341690063, "target_z": 0.34374997925956996, "ce": 6.24500846862793, "genuineness": 4.2249250411987305, "identity": 0.5194656848907471, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f8b7dac84e22fe936460018f7b3832a9d0846b4f2bbc7bb3d9c1edf2dee207ec.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "f8bf0466365490814f1bc22181cafa37db68724988ee3c3db82ebc21616f0e9f", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "114fa1b4f0a16f5974f53eb8593cd898a79897de5e4d21de07e805420758dbdb", "generation_seconds_batch": 22.687802717089653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.708385467529297, "target_z": 3.140625010370215, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.5824612379074097, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f8bf0466365490814f1bc22181cafa37db68724988ee3c3db82ebc21616f0e9f.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "f90af72eebd9a4e08cc57a768be3589fcd5c7bdd8b49acdb13c0ceb0c28bb80b", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6634353c7fb87969f62a8651a36f100dfa37a45510b3857e395574cb4a7a8894", "generation_seconds_batch": 23.620763604994863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0974643230438232, "target_z": 0.8984375155553225, "ce": 6.260893821716309, "genuineness": 3.8169827461242676, "identity": 0.5307580828666687, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f90af72eebd9a4e08cc57a768be3589fcd5c7bdd8b49acdb13c0ceb0c28bb80b.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "f90feb7f1571835a14cb3f326305af0828767f09ff2b090334bac6f4370e99fa", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a20dbe62313b04ead02c7d0193af4617512402d9e41dc150ba65c501001797b4", "generation_seconds_batch": 24.38813776895404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3491556644439697, "target_z": 2.640625010370215, "ce": 6.165581703186035, "genuineness": 3.8169827461242676, "identity": 0.3805907368659973, "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_Elation/f90feb7f1571835a14cb3f326305af0828767f09ff2b090334bac6f4370e99fa.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "f9abf112b642f667407afab0e92b988a853c12a5a3d9cfea4202f419aeef5041", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c4c622ffcf4382410db16c11c1bb839cd839e0e21c6913adc7dbe95ce995465a", "generation_seconds_batch": 25.473580107907765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4046138525009155, "target_z": -0.06591798138869955, "ce": 6.221180438995361, "genuineness": 4.356721878051758, "identity": 0.5926008224487305, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f9abf112b642f667407afab0e92b988a853c12a5a3d9cfea4202f419aeef5041.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": "f9c0ff2254440925dc7f4d28694472bcbb9a82a7e20a9cbf82bb70a46a1ac166", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ec937ee4252ef9f908d2784401506ee95ac1324cbec3049f7bda09c032ddcb6", "generation_seconds_batch": 22.61288313800469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7934720516204834, "target_z": 1.8671874948148925, "ce": 6.197352409362793, "genuineness": 4.080576419830322, "identity": 0.6779811382293701, "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_Elation/f9c0ff2254440925dc7f4d28694472bcbb9a82a7e20a9cbf82bb70a46a1ac166.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "f9d3c73de32fe476dc8a7668dfece8fcd287c923ab2f10799c0dc15e1d596991", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ecdd07aee297c358dc4af51306f78a2e77b4324239244227c639de43690af5a2", "generation_seconds_batch": 23.069029836100526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5296626091003418, "target_z": 1.4999999170382798, "ce": 6.23706579208374, "genuineness": 4.262581825256348, "identity": 0.6360021233558655, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.", "wer": 0.3684210526315789, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/f9d3c73de32fe476dc8a7668dfece8fcd287c923ab2f10799c0dc15e1d596991.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "fa09b5293c1d4a21b10a71d11694e8501a55f5d4adb10286c8dcee091a2100a2", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "312a585193df5494ebc7f70036b9e0380f37398b39dbf67fb88d3bca73d33a4a", "generation_seconds_batch": 21.030315508018248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0385282039642334, "target_z": 0.8164062940734138, "ce": 6.459460258483887, "genuineness": 4.293961524963379, "identity": 0.558860182762146, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fa09b5293c1d4a21b10a71d11694e8501a55f5d4adb10286c8dcee091a2100a2.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "fa31de105f121f3d3acfc5ec14adebd218f034d84b4d27a30967f3262dde4ada", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5a08477d2a50bf71952455801102ace5a715fb8ace848c425847e0c0d9b73e2e", "generation_seconds_batch": 21.23753822792787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8664405345916748, "target_z": 1.9687498962978498, "ce": 6.229123115539551, "genuineness": 4.042920112609863, "identity": 0.505039393901825, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinstehen.", "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_Elation/fa31de105f121f3d3acfc5ec14adebd218f034d84b4d27a30967f3262dde4ada.mp3" }, { "id": "emo_Elation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-fr-1", "key": "fa5a0ee9bab307070de4a4f6707d8619d5ca83ec1a82f45437a8abad0247ea03", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fbd2320f01d5a1a7d84b25e136c91999b0fecd239303869c84010a42e36c587b", "generation_seconds_batch": 25.1211202070117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0188827514648438, "target_z": 0.7890624429638174, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.7056248784065247, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fa5a0ee9bab307070de4a4f6707d8619d5ca83ec1a82f45437a8abad0247ea03.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "fa7f3c6ac9fedadf48f38c9b56184f4f77cec6dbf74a4f2b14e562e9a0cfc8fc", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a9fadc5e44ad4cf0954187e9ead8ba5581ed1d1324f89394aca91abcf397a136", "generation_seconds_batch": 23.675358145032078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3379297256469727, "target_z": 2.625, "ce": 5.879645347595215, "genuineness": 3.936227321624756, "identity": 0.3345711827278137, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fa7f3c6ac9fedadf48f38c9b56184f4f77cec6dbf74a4f2b14e562e9a0cfc8fc.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": "fa84d6f28fa45dd0ef6f8ba58c03c2c813b71c38501a99695f40170527bd47fb", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94b75e57f7f53f6676bb7aa511ab1da2ad9dbd15e0309f99d5d8d67a9dc40a2d", "generation_seconds_batch": 16.968050522962585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6400076150894165, "target_z": 0.26171875777766124, "ce": 6.197352409362793, "genuineness": 4.262581825256348, "identity": 0.6395325660705566, "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_Elation/fa84d6f28fa45dd0ef6f8ba58c03c2c813b71c38501a99695f40170527bd47fb.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "fafa6f919009e92c3899afa503f18caf71c56f766a4a3943ea245f9f1fa29827", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8c063eeab3b21c0a44a005bce36cca667e884d04d9f7fda52434a21fe4de3c3f", "generation_seconds_batch": 24.166899693082087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3242782950401306, "target_z": -0.17773436851861563, "ce": 6.213237762451172, "genuineness": 3.9048471450805664, "identity": 0.28668004274368286, "hypothesis": "The 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_Elation/fafa6f919009e92c3899afa503f18caf71c56f766a4a3943ea245f9f1fa29827.mp3" }, { "id": "emo_Elation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-0", "key": "fafdc3591594f34b8f368d3fb97fce58dce1f556e7add77b6b3afed5a84dd1cf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Die Tür ist noch offen.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0b2da099bc0bdb09090ea27beb37570f45450a17b017cf3d370c3c200dbdd23d", "generation_seconds_batch": 23.23096597904805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2714662551879883, "target_z": 1.140625010370215, "ce": 6.0305562019348145, "genuineness": 4.068024158477783, "identity": 0.28982338309288025, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fafdc3591594f34b8f368d3fb97fce58dce1f556e7add77b6b3afed5a84dd1cf.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": "fb1f5d8561aa5e1898cba57b75bc0f9fd7c5da4f14b3c167c4a246f93db8307c", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fadb590d110101a7bc827f53d73775e69c614041ec6e66d85de26988ca03a4cb", "generation_seconds_batch": 21.47142975591123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8729456663131714, "target_z": 0.5859374740744625, "ce": 6.157639026641846, "genuineness": 4.193545341491699, "identity": 0.6292398571968079, "hypothesis": "Welcome to placed the petite chaise blue. It is ici, pretty bibliothek. We remain after the deju.", "wer": 0.8571428571428571, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fb1f5d8561aa5e1898cba57b75bc0f9fd7c5da4f14b3c167c4a246f93db8307c.mp3" }, { "id": "emo_Elation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-es-1", "key": "fb3ed70b9411ae57f1d118fc0826505bde723daa6722f894a68a38f5650e6d04", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] He encontrado la cajita.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4522334ed8b534641a17032da1c872ac4a03fc050f9b860d62e759698215c817", "generation_seconds_batch": 22.318446271005087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7878592014312744, "target_z": 1.8593751555532252, "ce": 6.09409761428833, "genuineness": 4.250029563903809, "identity": 0.5340338945388794, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fb3ed70b9411ae57f1d118fc0826505bde723daa6722f894a68a38f5650e6d04.mp3" }, { "id": "emo_Elation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-0", "key": "fb440480ac723b52f7cfde5eeb88dbfc773a249ac46cb6d51b81151db4d432a0", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] The door is still open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "625482025461873dd608e01382bb675044125ec4246bb05cbee5925247a095d9", "generation_seconds_batch": 21.763898340053856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.203218460083008, "target_z": 2.4374998755574198, "ce": 5.49045467376709, "genuineness": 3.5847692489624023, "identity": 0.5755352973937988, "hypothesis": "The 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_Elation/fb440480ac723b52f7cfde5eeb88dbfc773a249ac46cb6d51b81151db4d432a0.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "fb81048d507b47ab198cc0619f1906c614ebd247ba1ae7576c2693c92f0f9536", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "44651cb2adb73ec4f9dd8069ad70459186d603f95d7809e0b4de454e03c1f428", "generation_seconds_batch": 22.999835808062926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.371607542037964, "target_z": 2.671875031110645, "ce": 6.284721851348877, "genuineness": 3.8546390533447266, "identity": 0.37448441982269287, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fb81048d507b47ab198cc0619f1906c614ebd247ba1ae7576c2693c92f0f9536.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": "fbe8b58833d44a527c3e8bc859ae8b3f77e0e545e704e924aa410c291bad68e9", "bucket": "emo_Elation", "phase": "heldout", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "298329f855648ac89d74e0728225d5ef680d1115b6e63c7f88f5b1b2cef4c741", "generation_seconds_batch": 22.09551269793883, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9964309334754944, "target_z": 0.7578125051851075, "ce": 6.316492557525635, "genuineness": 4.331617832183838, "identity": 0.6404663324356079, "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_Elation/fbe8b58833d44a527c3e8bc859ae8b3f77e0e545e704e924aa410c291bad68e9.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "fd7330d80cf885e4be01f200ce21e9c3b80a3472b2f0a5e17d76f8b9f6e18bdf", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bb74bd12dca52bb57a87110a3d0be15043d99026aefbdc796ca19d899acf3f92", "generation_seconds_batch": 24.6816872790223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3267037868499756, "target_z": 2.609374989629785, "ce": 6.260893821716309, "genuineness": 4.068024158477783, "identity": 0.5767290592193604, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fd7330d80cf885e4be01f200ce21e9c3b80a3472b2f0a5e17d76f8b9f6e18bdf.mp3" }, { "id": "emo_Elation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-1", "key": "fe66caf250c50723cb33a1632675fedd9e49ce4514675ceb5d902fa139bb55da", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b5163e8be9ef5fc25ec53f9ec20a93d4cb698c3e170b18ef151900fa858ec04", "generation_seconds_batch": 22.96093306108378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1474698781967163, "target_z": -0.42382811592606184, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.6027028560638428, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fe66caf250c50723cb33a1632675fedd9e49ce4514675ceb5d902fa139bb55da.mp3" }, { "id": "emo_Elation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-nl-0", "key": "fe6875f5e85061fffa94aa7318973a5410f675c53aa091a5019753e958cee970", "bucket": "emo_Elation", "phase": "wording", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] De deur staat nog open.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ce6c1dd4219fc267902d2d79cf7a75a6ff80dc2783236b49bea7fe6fd146c653", "generation_seconds_batch": 17.49216257291846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5502001643180847, "target_z": 0.13671875777766127, "ce": 6.070269584655762, "genuineness": 4.093128204345703, "identity": 0.39856353402137756, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/fe6875f5e85061fffa94aa7318973a5410f675c53aa091a5019753e958cee970.mp3" }, { "id": "emo_Elation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-de-1", "key": "ff4037db8de6b2d1f593d809ae66a33361a921a45e428395e20d7bb0c8d9cd5a", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0ca86a5b5ec8d82ad224917cd08b6c0e2f70edff85222010e0acefc21c19ee67", "generation_seconds_batch": 21.030315508018248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9122364521026611, "target_z": 0.640625010370215, "ce": 6.372091293334961, "genuineness": 4.18726921081543, "identity": 0.5938369035720825, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ff4037db8de6b2d1f593d809ae66a33361a921a45e428395e20d7bb0c8d9cd5a.mp3" }, { "id": "emo_Elation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Elation-en-1", "key": "ffb98da5400b20f06525cd6fe05ca76ca614f4f95a87d8eee258646ce72665d5", "bucket": "emo_Elation", "phase": "grid", "candidate": "manual-a8a332cdd043", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Adopt a grand, expansive vocal projection, as if sharing monumental good news with the world.\nSCRIPT:\n(Project the initial sounds with full chest resonance, conveying overwhelming, open-hearted gladness.) [3.2 seconds duration] I found the little box.\n(Expand the vocal space during the middle, letting the sound swell with expansive, unrestrained glee.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final words with a powerful, sustained upward thrust, a triumphant vocal peak.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "edc7d9d88215125616eea445bd1b75e3e8975b59cb3e134f0f53b651144699c9", "generation_seconds_batch": 16.704456723993644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3258116245269775, "target_z": 3.99999991703828, "ce": 5.303802013397217, "genuineness": 3.9550557136535645, "identity": 0.5105925798416138, "hypothesis": "I found the little box! It was beside the old window! We can look inside together!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Elation/ffb98da5400b20f06525cd6fe05ca76ca614f4f95a87d8eee258646ce72665d5.mp3" }, { "key": "original-emo_Elation-de-0-seed1701-scale0.0", "bucket": "emo_Elation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "cac62d1c5d60b99492b5c27a06352673fedc18fdb3c5bdc9af40f9eb1339bf9d", "task_id": "emo_Elation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.21342222392559052, "target_z": -0.33203124222233876, "ce": 6.284721851348877, "genuineness": 4.356721878051758, "identity": 0.5308493375778198, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/4fa7fa1aecef8ba2714173b7.mp3" }, { "key": "original-emo_Elation-de-0-seed1701-scale0.5", "bucket": "emo_Elation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "86ce608d6c6f43d4bdff9e159fdecb3caaae3abf127450e0b1d46125c47a5b75", "task_id": "emo_Elation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.07029157876968384, "target_z": -0.53125002074043, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.6178779602050781, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/04269870b4c4c6d3c49c0332.mp3" }, { "key": "original-emo_Elation-de-0-seed1701-scale0.75", "bucket": "emo_Elation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "d920b1a230c1ce69d0e2bb5a5c871389949f0d97bf4ed9b7100ee49d77b64444", "task_id": "emo_Elation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.14045366644859314, "target_z": -0.4335937474074463, "ce": 6.1894097328186035, "genuineness": 4.595211505889893, "identity": 0.6234580278396606, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/1e5272f187cfeae2e7515e6e.mp3" }, { "key": "original-emo_Elation-de-0-seed1701-scale1.0", "bucket": "emo_Elation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "1cf742ef8a71963089ff2d64070921f2afdb3b4596a2c476a5d9019185f2c74b", "task_id": "emo_Elation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.10958236455917358, "target_z": -0.47656248444467747, "ce": 6.205295085906982, "genuineness": 4.319066047668457, "identity": 0.6460314989089966, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/1be4ba3ecf18f6e9676226b0.mp3" }, { "key": "original-emo_Elation-de-0-seed1702-scale0.0", "bucket": "emo_Elation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "5b05dce4840a2f3e2cbdb4e6a3d6ea20f98848927b2fcbc115997c2a7b001d5a", "task_id": "emo_Elation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.12080827355384827, "target_z": -0.46093751555532253, "ce": 6.2767791748046875, "genuineness": 4.6705241203308105, "identity": 0.6978460550308228, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/119cf578fa70b3e2ed5ad998.mp3" }, { "key": "original-emo_Elation-de-0-seed1702-scale0.5", "bucket": "emo_Elation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "556d9f925d570c4454138ad2ebc56e282c9c95308c3db49d024493784903dc31", "task_id": "emo_Elation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.08432400226593018, "target_z": -0.5117187577776613, "ce": 6.09409761428833, "genuineness": 4.3127899169921875, "identity": 0.45868751406669617, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/0c854f5fbef646126d255f5e.mp3" }, { "key": "original-emo_Elation-de-0-seed1702-scale0.75", "bucket": "emo_Elation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "7f338f92e6e3eb272ff384ac1c6d8feb1c57c33721893a88f205f1577a684bea", "task_id": "emo_Elation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.08993697166442871, "target_z": -0.5039062525925537, "ce": 6.165581703186035, "genuineness": 4.406930446624756, "identity": 0.38194018602371216, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/9245e9ca58ea3f8fb6fb468c.mp3" }, { "key": "original-emo_Elation-de-0-seed1702-scale1.0", "bucket": "emo_Elation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "93b251f096c61efc1ac685ac5afcea97cb9c3c6981337ea92286a3fe261cf005", "task_id": "emo_Elation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.12501800060272217, "target_z": -0.4550781366664919, "ce": 6.213237762451172, "genuineness": 4.268857479095459, "identity": 0.5782732963562012, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/a8ca9ba6cb153243f9906d30.mp3" }, { "key": "original-emo_Elation-de-1-seed1701-scale0.0", "bucket": "emo_Elation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "ae8c5479df2de05688d805268b60ab92232f277c5863bfe2da808db2861ee5ce", "task_id": "emo_Elation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.388827383518219, "target_z": -0.08789064185159941, "ce": 6.316492557525635, "genuineness": 4.193545341491699, "identity": 0.4863229990005493, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/8a833eaf878c84bf856eb226.mp3" }, { "key": "original-emo_Elation-de-1-seed1701-scale0.5", "bucket": "emo_Elation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "9e57704ce0a6e9bc7198f4e53a3886b9d7c61b632faaaa7950ca5198250e0cf9", "task_id": "emo_Elation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.5712487697601318, "target_z": 0.16601561074095436, "ce": 6.3641486167907715, "genuineness": 4.557555198669434, "identity": 0.4789098799228668, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/9990133cefeee58da9e71cfb.mp3" }, { "key": "original-emo_Elation-de-1-seed1701-scale0.75", "bucket": "emo_Elation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "9aaf1d03caddc42de77ae5088b391b69ac1be9f3d5846fbd2fd26c64e73edf1e", "task_id": "emo_Elation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.6975405216217041, "target_z": 0.3417968944441532, "ce": 6.23706579208374, "genuineness": 4.419482707977295, "identity": 0.5829909443855286, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/f7a48e86b10cfab7ff707ab1.mp3" }, { "key": "original-emo_Elation-de-1-seed1701-scale1.0", "bucket": "emo_Elation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "4077bbf78a03e6b9d815b038c982983cc8589b8d0eac25c8f8549e7b4a1de907", "task_id": "emo_Elation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.266745388507843, "target_z": -0.2578125051851075, "ce": 6.459460258483887, "genuineness": 4.3127899169921875, "identity": 0.2830653190612793, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/1cc61b97a572878a31d648a9.mp3" }, { "key": "original-emo_Elation-de-1-seed1702-scale0.0", "bucket": "emo_Elation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "5bf88c563f9694cf2cc8ea3ec29908e4c0d2a1128aa8f005d9780d19e626f243", "task_id": "emo_Elation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.39163386821746826, "target_z": -0.08398438925904565, "ce": 6.308549880981445, "genuineness": 4.356721878051758, "identity": 0.3473549485206604, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/23a036683d4bbdd406d3bb19.mp3" }, { "key": "original-emo_Elation-de-1-seed1702-scale0.5", "bucket": "emo_Elation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "31a0e32ee2ea12987c859caa6d87ab5fd54ed75595dd3e233b59af6522b80e76", "task_id": "emo_Elation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.24429352581501007, "target_z": -0.2890625051851075, "ce": 6.38003396987915, "genuineness": 4.394378662109375, "identity": 0.48569774627685547, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/2d2823f45776844e38a3db22.mp3" }, { "key": "original-emo_Elation-de-1-seed1702-scale0.75", "bucket": "emo_Elation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "a1fa219b784c5f183bb609777b04134684f7d7e78e3ab5656c9880eb84f649c0", "task_id": "emo_Elation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.11940503120422363, "target_z": -0.4628906418515994, "ce": 6.435632705688477, "genuineness": 4.6705241203308105, "identity": 0.5435550212860107, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/0c6d7484161115a190843dd3.mp3" }, { "key": "original-emo_Elation-de-1-seed1702-scale1.0", "bucket": "emo_Elation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "adefbb8ba2b2f1654289976b1f723d2a23b6eb8926cbc8ecfb2a9dd5bd88d772", "task_id": "emo_Elation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.30252805352211, "target_z": -0.20800780537047717, "ce": 6.4515180587768555, "genuineness": 4.325342178344727, "identity": 0.5668289661407471, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/de/96cb4c8609ece3d895b04267.mp3" }, { "key": "original-emo_Elation-en-0-seed1701-scale0.0", "bucket": "emo_Elation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "a2ab3fd8075dccf203364054887dd89ac76abe886172da5e8f8f3bec7ee22aae", "task_id": "emo_Elation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.0029360055923461914, "target_z": -0.625, "ce": 6.141753673553467, "genuineness": 3.9676074981689453, "identity": 0.45328688621520996, "hypothesis": "The 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_Elation/en/7262f38a580bfb848bf246fb.mp3" }, { "key": "original-emo_Elation-en-0-seed1701-scale0.5", "bucket": "emo_Elation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "f2ae0d59234a72fa48d5056535544f911f2813d0c3ef850cf366b86b7b0b7d38", "task_id": "emo_Elation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": -0.06441956758499146, "target_z": -0.71874997925957, "ce": 6.300607204437256, "genuineness": 4.18099308013916, "identity": 0.2953173816204071, "hypothesis": "The 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_Elation/en/99fe6eb4c5777295b8c68c78.mp3" }, { "key": "original-emo_Elation-en-0-seed1701-scale0.75", "bucket": "emo_Elation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "383963c166146b0d841725abc4ddbd315bfe96341834808f8563b33ac47619f4", "task_id": "emo_Elation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": -0.053193628787994385, "target_z": -0.7031249688893549, "ce": 6.260893821716309, "genuineness": 3.936227321624756, "identity": 0.4013817310333252, "hypothesis": "The 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_Elation/en/e1d2504f9df3e2e86dbd16c9.mp3" }, { "key": "original-emo_Elation-en-0-seed1701-scale1.0", "bucket": "emo_Elation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "8efb2583d9debb3facbffc6450b402a1b4bae826a6ef0878ccfad073a1a0bda4", "task_id": "emo_Elation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.0029360055923461914, "target_z": -0.625, "ce": 6.252951145172119, "genuineness": 4.080576419830322, "identity": 0.35880208015441895, "hypothesis": "The 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_Elation/en/9934cb442ae494de3c38141d.mp3" }, { "key": "original-emo_Elation-en-0-seed1702-scale0.0", "bucket": "emo_Elation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "fa47965f4668e5895eef2fb2e1b9e7b36e1d950cb8793f6539c8e087d2d63a00", "task_id": "emo_Elation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": -0.02232232689857483, "target_z": -0.6601562318521237, "ce": 6.141753673553467, "genuineness": 3.8671910762786865, "identity": 0.23794732987880707, "hypothesis": "The 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_Elation/en/369c05d92210b7e10e3e038c.mp3" }, { "key": "original-emo_Elation-en-0-seed1702-scale0.5", "bucket": "emo_Elation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "86555ed0a8f44b08a4e5c23e43891e7376c7bb95987b5aa620dd332bd349475e", "task_id": "emo_Elation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.10396939516067505, "target_z": -0.484374989629785, "ce": 6.205295085906982, "genuineness": 4.118232727050781, "identity": 0.36330345273017883, "hypothesis": "The 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_Elation/en/4b01c1fc8c0bf93c6f27edfe.mp3" }, { "key": "original-emo_Elation-en-0-seed1702-scale0.75", "bucket": "emo_Elation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "0483ccc6b0066a22ab409b16e2c32512c0ba9df8d06205d9cbcc71b0d0ad7155", "task_id": "emo_Elation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": -0.005483448505401611, "target_z": -0.6367187577776613, "ce": 6.141753673553467, "genuineness": 3.9425034523010254, "identity": 0.24327930808067322, "hypothesis": "The 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_Elation/en/722dd53ec645c31a667e0c59.mp3" }, { "key": "original-emo_Elation-en-0-seed1702-scale1.0", "bucket": "emo_Elation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "1b073ff4b37d9a8123d46e20760dc762485fed3ba8435fad86cc1ab69d6eb0be", "task_id": "emo_Elation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.047839730978012085, "target_z": -0.5625, "ce": 6.141753673553467, "genuineness": 3.8169827461242676, "identity": 0.40784552693367004, "hypothesis": "The 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_Elation/en/9bc84634e72bd2f6395d93d2.mp3" }, { "key": "original-emo_Elation-en-1-seed1701-scale0.0", "bucket": "emo_Elation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "85779d62137b4bd1de05cf7c4e3794452bf78ff7bd6c972855c5224cadaba549", "task_id": "emo_Elation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.8252354860305786, "target_z": 0.5195312629627687, "ce": 6.38003396987915, "genuineness": 4.331617832183838, "identity": 0.39615771174430847, "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_Elation/en/259731a4cb82d8d92ae00dc5.mp3" }, { "key": "original-emo_Elation-en-1-seed1701-scale0.5", "bucket": "emo_Elation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "d1d28499da1e169e5731b332545ff9d2d91e22c670d3100d00bdd9f138fb2b93", "task_id": "emo_Elation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.7242020964622498, "target_z": 0.3789062525925537, "ce": 6.284721851348877, "genuineness": 4.231201171875, "identity": 0.4514061510562897, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/en/46a929de3b9a839d6db02183.mp3" }, { "key": "original-emo_Elation-en-1-seed1701-scale0.75", "bucket": "emo_Elation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "62d939fc5ce86e275a780e7041aee50ede56049194e88345d120e4867466b50f", "task_id": "emo_Elation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.6484270691871643, "target_z": 0.27343751555532253, "ce": 6.38797664642334, "genuineness": 4.21237325668335, "identity": 0.5218485593795776, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/en/46f218be8d8a22cd89c250fb.mp3" }, { "key": "original-emo_Elation-en-1-seed1701-scale1.0", "bucket": "emo_Elation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "68908426cba08da5464aaa954caaf9e3be69069920be2b20b3a9462fdd93363c", "task_id": "emo_Elation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.6708788871765137, "target_z": 0.3046874533340324, "ce": 6.38797664642334, "genuineness": 4.406930446624756, "identity": 0.3432376980781555, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/en/cf0a7ebdf47e56deaf903b39.mp3" }, { "key": "original-emo_Elation-en-1-seed1702-scale0.0", "bucket": "emo_Elation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "68554a141594a297c1b9fa58c24860156f018d7f71ab44344a8b952ee5b789db", "task_id": "emo_Elation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.5600228309631348, "target_z": 0.15039060037073934, "ce": 6.300607204437256, "genuineness": 4.432034492492676, "identity": 0.46155914664268494, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/en/bc596a281f2444a474ad050f.mp3" }, { "key": "original-emo_Elation-en-1-seed1702-scale0.5", "bucket": "emo_Elation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "dbce6466ae6db8d9b482467102790e70b3d63b93ac1d10924fd671a21ef0629e", "task_id": "emo_Elation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.19938981533050537, "target_z": -0.35156248444467747, "ce": 6.41180419921875, "genuineness": 4.582659721374512, "identity": 0.4269738793373108, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/en/759835c9494af7b65c13ef2c.mp3" }, { "key": "original-emo_Elation-en-1-seed1702-scale0.75", "bucket": "emo_Elation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "f127ab9974b3acd8e4069d6453ebb3a3f869ce47c611bf080da269860443b8fe", "task_id": "emo_Elation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.6652659177780151, "target_z": 0.2968749481489249, "ce": 6.284721851348877, "genuineness": 4.3127899169921875, "identity": 0.4433475136756897, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/en/c946eab6d89b9f2ea5795d64.mp3" }, { "key": "original-emo_Elation-en-1-seed1702-scale1.0", "bucket": "emo_Elation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "adf4bea587d29720e22aaf3969c133e4dc6a415f4436ec2f47fea78e24dc0a8a", "task_id": "emo_Elation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.16571199893951416, "target_z": -0.39843751555532253, "ce": 6.340320587158203, "genuineness": 4.425758361816406, "identity": 0.24222305417060852, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/en/a77743d05f48cc26258cf723.mp3" }, { "key": "original-emo_Elation-es-0-seed1701-scale0.0", "bucket": "emo_Elation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "d7c6344410c4d7f6c33b862fcb065c1b7ba01acb35b89403e26890bc4486e8d8", "task_id": "emo_Elation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.07590454816818237, "target_z": -0.5234375155553225, "ce": 6.1020402908325195, "genuineness": 4.607763767242432, "identity": 0.5707764625549316, "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_Elation/es/85bd13c771dc3f1dff5ab906.mp3" }, { "key": "original-emo_Elation-es-0-seed1701-scale0.5", "bucket": "emo_Elation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "c6222ae6844cb617bc1667491da48567e858cf0222603cdfaa0ca90a5ed70cd0", "task_id": "emo_Elation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.008548974990844727, "target_z": -0.6171874948148925, "ce": 6.054384231567383, "genuineness": 3.936227321624756, "identity": 0.4681398272514343, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/a50aee06e682737c10429207.mp3" }, { "key": "original-emo_Elation-es-0-seed1701-scale0.75", "bucket": "emo_Elation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "4c2f697759fbcb193c311cc5dea2ab1689d06913170ff09753777e081a6524bf", "task_id": "emo_Elation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.08993697166442871, "target_z": -0.5039062525925537, "ce": 5.982900142669678, "genuineness": 4.093128204345703, "identity": 0.503744900226593, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/7e6ac30f2387166ed7813691.mp3" }, { "key": "original-emo_Elation-es-0-seed1701-scale1.0", "bucket": "emo_Elation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "238aa9b279d56fa5709b7b21395f834662583d9fd8eb998965c7e7ca26a3c787", "task_id": "emo_Elation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.07029157876968384, "target_z": -0.53125002074043, "ce": 6.125868320465088, "genuineness": 4.13078498840332, "identity": 0.6265506744384766, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/39820ade77a6e69ee51fd1dd.mp3" }, { "key": "original-emo_Elation-es-0-seed1702-scale0.0", "bucket": "emo_Elation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "e6e89f05cc83bef64d5827ac47ea8ba8a1fa95613d7d7f9ad3d91725c956067f", "task_id": "emo_Elation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.07871103286743164, "target_z": -0.5195312629627687, "ce": 5.982900142669678, "genuineness": 3.7918784618377686, "identity": 0.44605106115341187, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/c8306a4a61ada1241573fe9f.mp3" }, { "key": "original-emo_Elation-es-0-seed1702-scale0.5", "bucket": "emo_Elation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "003530b3fe2fcb47a62a071b28efbf0845c54aa75e52ef6f9dbddc0470bf099b", "task_id": "emo_Elation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.09835642576217651, "target_z": -0.4921874948148925, "ce": 5.974957466125488, "genuineness": 4.595211505889893, "identity": 0.5482004880905151, "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_Elation/es/06f0315eef77bad54b7faa6c.mp3" }, { "key": "original-emo_Elation-es-0-seed1702-scale0.75", "bucket": "emo_Elation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "e33862d46cd49d814a3bf0f72ab8c8e3c9307024c7eb5c9e65828b733da9a834", "task_id": "emo_Elation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.09274345636367798, "target_z": -0.5, "ce": 6.054384231567383, "genuineness": 4.356721878051758, "identity": 0.6029286980628967, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/6de2deb585ae6cfaabdced97.mp3" }, { "key": "original-emo_Elation-es-0-seed1702-scale1.0", "bucket": "emo_Elation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "7612e5ff67ccb91f3137d2f8565cdf57b646db96b1955d96a7c591d638ea2408", "task_id": "emo_Elation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.06467863917350769, "target_z": -0.5390624844446775, "ce": 6.070269584655762, "genuineness": 4.005263805389404, "identity": 0.39455029368400574, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/f4763a256dda487e30feb4c2.mp3" }, { "key": "original-emo_Elation-es-1-seed1701-scale0.0", "bucket": "emo_Elation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "5675b14d561215a62bf986915947ec2bacdd39b7fb82f40c3e549fc989d1e92d", "task_id": "emo_Elation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.26393890380859375, "target_z": -0.26171875777766124, "ce": 6.125868320465088, "genuineness": 4.143336772918701, "identity": 0.518989622592926, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/eda9076037615e9df6445e3b.mp3" }, { "key": "original-emo_Elation-es-1-seed1701-scale0.5", "bucket": "emo_Elation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "9a8db287128238505901874066b19425210832a7c0f0ac2719491ca81c6944ae", "task_id": "emo_Elation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.1713249683380127, "target_z": -0.390625010370215, "ce": 6.117925643920898, "genuineness": 4.432034492492676, "identity": 0.7126590013504028, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/f381998f71b90399642b84a1.mp3" }, { "key": "original-emo_Elation-es-1-seed1701-scale0.75", "bucket": "emo_Elation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "11fddb9ef19111599fc9a84756ea940d9d7c0c23f50c27e1af4f56666600db9b", "task_id": "emo_Elation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.6484270691871643, "target_z": 0.27343751555532253, "ce": 6.070269584655762, "genuineness": 4.457139015197754, "identity": 0.6598035097122192, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/c592b52f4d88abea0c4d5f50.mp3" }, { "key": "original-emo_Elation-es-1-seed1701-scale1.0", "bucket": "emo_Elation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "706746a5ad5413f3beca1b1eb491026bbae7131b5d356402b31df65bfeb3ff15", "task_id": "emo_Elation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.2092124968767166, "target_z": -0.33789062111116935, "ce": 6.133810997009277, "genuineness": 4.519899368286133, "identity": 0.7042077779769897, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/6876a27f8560f67726420f6a.mp3" }, { "key": "original-emo_Elation-es-1-seed1702-scale0.0", "bucket": "emo_Elation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "15a6255308845c9aad50b3358c3e1e1707fac2ba4c4020aaf8587c66134b823e", "task_id": "emo_Elation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.15869581699371338, "target_z": -0.4082031055558468, "ce": 6.0146708488464355, "genuineness": 4.306513786315918, "identity": 0.6045494079589844, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/b44c40acb231673b61f99789.mp3" }, { "key": "original-emo_Elation-es-1-seed1702-scale0.5", "bucket": "emo_Elation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "1ad70e4f5fd7a5fb10b1de14cc7e6f137321be2971028e23c42ef3e4a4c983c6", "task_id": "emo_Elation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.15308284759521484, "target_z": -0.41601561074095433, "ce": 6.221180438995361, "genuineness": 4.444586753845215, "identity": 0.6404687166213989, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/5c85205d9e3a434ba1404087.mp3" }, { "key": "original-emo_Elation-es-1-seed1702-scale0.75", "bucket": "emo_Elation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "27339ae13bb2cf6cc7a9b7b2619c763d4816d5788273961886deb5b9d14cf2ea", "task_id": "emo_Elation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.3846176862716675, "target_z": -0.09374997925956996, "ce": 6.0305562019348145, "genuineness": 4.6705241203308105, "identity": 0.5449697971343994, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/ea7b67939eba8613c389add3.mp3" }, { "key": "original-emo_Elation-es-1-seed1702-scale1.0", "bucket": "emo_Elation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "182b33ca20127150419151b9a30a952422a09a4017311d66a0a017289b210ed3", "task_id": "emo_Elation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.16992172598838806, "target_z": -0.3925781366664919, "ce": 6.1020402908325195, "genuineness": 4.482243061065674, "identity": 0.5762096047401428, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/es/9091f58d45dc13fa36ed8d7f.mp3" }, { "key": "original-emo_Elation-fr-0-seed1701-scale0.0", "bucket": "emo_Elation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "e4aa1ff98594d836bdb6a2a6d45ff85e74ec3231032479913c7b3e762e3d2eb1", "task_id": "emo_Elation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.06467863917350769, "target_z": -0.5390624844446775, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.779875636100769, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/907b815d1bd14d10229ce734.mp3" }, { "key": "original-emo_Elation-fr-0-seed1701-scale0.5", "bucket": "emo_Elation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "81fb9912b789a2ce712eb8e805d22b6d02eeddf3423464400bf80a5fed2b57ad", "task_id": "emo_Elation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": -0.008289933204650879, "target_z": -0.640625010370215, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.7472020983695984, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/07a3f32acdf973b19dfe8ac8.mp3" }, { "key": "original-emo_Elation-fr-0-seed1701-scale0.75", "bucket": "emo_Elation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "f6356c1d398a4995a393d8590a301c12e6971727ad095cfc8973de0eb80cafd2", "task_id": "emo_Elation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.06748512387275696, "target_z": -0.5351562318521237, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.6988109350204468, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/d8de87133982a2057a5814c4.mp3" }, { "key": "original-emo_Elation-fr-0-seed1701-scale1.0", "bucket": "emo_Elation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "e2a93ff2ad6b0a3566cb5af62af5c19f1a22f8721f8193a2c5810ce03183b154", "task_id": "emo_Elation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": -0.039161235094070435, "target_z": -0.6835937474074463, "ce": 6.078212261199951, "genuineness": 4.469690799713135, "identity": 0.7699217796325684, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/85c8d82b50b16f14b06743e3.mp3" }, { "key": "original-emo_Elation-fr-0-seed1702-scale0.0", "bucket": "emo_Elation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "5e039a1f978e9de60ba53c36d0e0fb6b404f9aaf0d8635d01ce41827065f1bf4", "task_id": "emo_Elation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.03380730748176575, "target_z": -0.5820312629627687, "ce": 6.157639026641846, "genuineness": 4.406930446624756, "identity": 0.7412337064743042, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/596210f550978c253d1d2fb5.mp3" }, { "key": "original-emo_Elation-fr-0-seed1702-scale0.5", "bucket": "emo_Elation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "4cca3b8f9ab257c92c142eb9ad7ed43f4fc140f8fbccf8d5dcbbaad2dbf177eb", "task_id": "emo_Elation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": -0.030741780996322632, "target_z": -0.671874989629785, "ce": 6.054384231567383, "genuineness": 4.2374773025512695, "identity": 0.804621696472168, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/a3c5f33d946d57af84e6109e.mp3" }, { "key": "original-emo_Elation-fr-0-seed1702-scale0.75", "bucket": "emo_Elation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "dfb2d3ade645f2a363a32f54584ff574753e342cf3923f62e9b5c1244d050009", "task_id": "emo_Elation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.059065669775009155, "target_z": -0.546874989629785, "ce": 6.157639026641846, "genuineness": 3.9048471450805664, "identity": 0.7112013697624207, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/6f971915f74353e9f680ba4d.mp3" }, { "key": "original-emo_Elation-fr-0-seed1702-scale1.0", "bucket": "emo_Elation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "ac4fad8af4f7d20058d8c5faea1832183e4bbd667feecc6620057f6758c02cd6", "task_id": "emo_Elation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.008548974990844727, "target_z": -0.6171874948148925, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.7062518000602722, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. C'est chez Zéis.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/0003aa1009f6a5539e124d20.mp3" }, { "key": "original-emo_Elation-fr-1-seed1701-scale0.0", "bucket": "emo_Elation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "58e13955927a0b0c259c2441ff7416ceed72c6350e27a100936543aea195d8d4", "task_id": "emo_Elation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.028194338083267212, "target_z": -0.5898437681478763, "ce": 6.324435234069824, "genuineness": 4.808597087860107, "identity": 0.6987308263778687, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/9b4d1199e39ef6b8fa043651.mp3" }, { "key": "original-emo_Elation-fr-1-seed1701-scale0.5", "bucket": "emo_Elation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "03d85375ba0b5a6064308da7eb63093306d5b756459a978f409b31bd82e3324f", "task_id": "emo_Elation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.24710001051425934, "target_z": -0.2851562525925537, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.707427978515625, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/cf4a09cce6caece569c777b7.mp3" }, { "key": "original-emo_Elation-fr-1-seed1701-scale0.75", "bucket": "emo_Elation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "29db953242e67fd6680d5132bcc236832ee6dcea877fb3e673dc30a6e59c9420", "task_id": "emo_Elation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.09554994106292725, "target_z": -0.4960937474074463, "ce": 6.23706579208374, "genuineness": 4.419482707977295, "identity": 0.7120674848556519, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/cafa1750c21d4621b689aca4.mp3" }, { "key": "original-emo_Elation-fr-1-seed1701-scale1.0", "bucket": "emo_Elation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "d4bf2edfb3150e389efb65ee80dae5c79024714780c117fac06b12cb9827afcb", "task_id": "emo_Elation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.23868057131767273, "target_z": -0.296874989629785, "ce": 6.133810997009277, "genuineness": 4.369274139404297, "identity": 0.7578945159912109, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/d7c98bec2fe79ff5245a97ce.mp3" }, { "key": "original-emo_Elation-fr-1-seed1702-scale0.0", "bucket": "emo_Elation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "50a75e1c60dbdf1f9d718e89c738caedb66ccb3215e306b1aa9acac180170521", "task_id": "emo_Elation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.07590454816818237, "target_z": -0.5234375155553225, "ce": 6.09409761428833, "genuineness": 4.519899368286133, "identity": 0.825838565826416, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/24f05079e2ae3c1356a47784.mp3" }, { "key": "original-emo_Elation-fr-1-seed1702-scale0.5", "bucket": "emo_Elation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "38c38a66ea2a8d625382b05ed57d967ba5d9c24476954b09529f99fa56742f93", "task_id": "emo_Elation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.18255090713500977, "target_z": -0.375, "ce": 6.205295085906982, "genuineness": 4.545003414154053, "identity": 0.7918029427528381, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/c762fcf87ca19bddf5c1d745.mp3" }, { "key": "original-emo_Elation-fr-1-seed1702-scale0.75", "bucket": "emo_Elation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "b66474c7c3016db21f1bd939c71af575ed48c0045997ad30e5f23086badb341c", "task_id": "emo_Elation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.14606663584709167, "target_z": -0.42578124222233876, "ce": 6.165581703186035, "genuineness": 4.7458367347717285, "identity": 0.7766380310058594, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/0b1788a17d297a6a0a9bbcfb.mp3" }, { "key": "original-emo_Elation-fr-1-seed1702-scale1.0", "bucket": "emo_Elation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "3953b8db453e8c1df366501d19ab0b46ec2af93dee606144e50e78a47f2f26a0", "task_id": "emo_Elation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": -0.005483448505401611, "target_z": -0.6367187577776613, "ce": 6.197352409362793, "genuineness": 4.808597087860107, "identity": 0.7334880232810974, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/fr/8bb5da1488e8fc9e19b6d7d2.mp3" }, { "key": "original-emo_Elation-nl-0-seed1701-scale0.0", "bucket": "emo_Elation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "520208a963978c57764345d4f799150464ebbcc3b9e4c78a489adfa361e04b48", "task_id": "emo_Elation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.2737616002559662, "target_z": -0.24804687370372314, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.7622760534286499, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/43ad6e5fb4e6c51d0ce529bb.mp3" }, { "key": "original-emo_Elation-nl-0-seed1701-scale0.5", "bucket": "emo_Elation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "1a81fdf8e0b176df1729c04a53c4c3625854155cd882612a1173369b1002871f", "task_id": "emo_Elation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.22184166312217712, "target_z": -0.3203125051851075, "ce": 6.006728172302246, "genuineness": 4.042920112609863, "identity": 0.5243329405784607, "hypothesis": "De deur 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_Elation/nl/dddf32faf8241a79a9567289.mp3" }, { "key": "original-emo_Elation-nl-0-seed1701-scale0.75", "bucket": "emo_Elation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "7b80acdaeb40aeb0efd9bbf14ee44f233deded5b1ec10bf31b0b9b5caf89c52e", "task_id": "emo_Elation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.17413145303726196, "target_z": -0.38671875777766124, "ce": 6.078212261199951, "genuineness": 4.344170093536377, "identity": 0.8541110754013062, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/c5f30eefb88bf22de471f52e.mp3" }, { "key": "original-emo_Elation-nl-0-seed1701-scale1.0", "bucket": "emo_Elation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "7fcb40be21cad4c1ff965ec6dab02c94f37ffdaf8622b835f647d352d50b53bd", "task_id": "emo_Elation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.16571199893951416, "target_z": -0.39843751555532253, "ce": 6.117925643920898, "genuineness": 4.218649387359619, "identity": 0.4564850628376007, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/2878a51bd40c4fcba8414f7b.mp3" }, { "key": "original-emo_Elation-nl-0-seed1702-scale0.0", "bucket": "emo_Elation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "ce467090878bc1218c3288bf0d59375801f4d71ae3b6d08b2aa6539b7943aa0f", "task_id": "emo_Elation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.10396939516067505, "target_z": -0.484374989629785, "ce": 6.157639026641846, "genuineness": 4.419482707977295, "identity": 0.6634484529495239, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/0d538dda18e6d997f0ea63d9.mp3" }, { "key": "original-emo_Elation-nl-0-seed1702-scale0.5", "bucket": "emo_Elation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "0998506ea67feea5d720cbbd28264e653c86af8e7e8000b7ec46fb21ba4887c0", "task_id": "emo_Elation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.12080827355384827, "target_z": -0.46093751555532253, "ce": 6.125868320465088, "genuineness": 4.356721878051758, "identity": 0.6207833290100098, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/42d882f1cd777810e21753a1.mp3" }, { "key": "original-emo_Elation-nl-0-seed1702-scale0.75", "bucket": "emo_Elation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "6858881981cc2a4dedcf562966d1988f577059d1064a390b72f813b72c0bd3f6", "task_id": "emo_Elation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.17272821068763733, "target_z": -0.38867188407393816, "ce": 5.998785495758057, "genuineness": 4.281409740447998, "identity": 0.6162624955177307, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/0bc98812fa5e26744f85ca33.mp3" }, { "key": "original-emo_Elation-nl-0-seed1702-scale1.0", "bucket": "emo_Elation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "fd91a8984d27382d096779ea88816b64915556bd763a5e30ea7277338ecb9bdf", "task_id": "emo_Elation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.18535739183425903, "target_z": -0.3710937474074463, "ce": 6.022613525390625, "genuineness": 4.325342178344727, "identity": 0.5115869045257568, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/d3fc67b8e21ea25f722150d3.mp3" }, { "key": "original-emo_Elation-nl-1-seed1701-scale0.0", "bucket": "emo_Elation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "636baf2ba41f0a49c20edd129c1074c495e12abce740519726a1b3026cc69100", "task_id": "emo_Elation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.2456967681646347, "target_z": -0.28710937888883065, "ce": 6.213237762451172, "genuineness": 4.394378662109375, "identity": 0.7008264660835266, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/f953aaca58f47dd63e962e1f.mp3" }, { "key": "original-emo_Elation-nl-1-seed1701-scale0.5", "bucket": "emo_Elation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "53c86a18bce9bf8745798dab05d5ad2460610474333746a6348940c6a610309b", "task_id": "emo_Elation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.13624393939971924, "target_z": -0.43945312629627686, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.7755616903305054, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/c0de4481930f3cb121b371c7.mp3" }, { "key": "original-emo_Elation-nl-1-seed1701-scale0.75", "bucket": "emo_Elation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "d3f3bd530bae29a824dc38db2f12e6e43690b4ec3dc39c160151fcaacb4bcf08", "task_id": "emo_Elation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.22324490547180176, "target_z": -0.31835937888883065, "ce": 6.149696350097656, "genuineness": 4.168440818786621, "identity": 0.5249032974243164, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/e6291601f015932a410df294.mp3" }, { "key": "original-emo_Elation-nl-1-seed1701-scale1.0", "bucket": "emo_Elation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "e0fe4fe28466360953e6780c0b14987b1363d4d7b679ccdec1de3fa93a946482", "task_id": "emo_Elation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.22605139017105103, "target_z": -0.31445312629627686, "ce": 6.109982967376709, "genuineness": 4.507347106933594, "identity": 0.6553912162780762, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/6aa8e04b62be606898df89f2.mp3" }, { "key": "original-emo_Elation-nl-1-seed1702-scale0.0", "bucket": "emo_Elation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "1421ff363baac703525eb7150b9cc52cb14bc951e0e557ed0dbfb8a8cd6a0e9a", "task_id": "emo_Elation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.13343745470046997, "target_z": -0.44335937888883065, "ce": 6.356205940246582, "genuineness": 4.444586753845215, "identity": 0.6634393930435181, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samenheen kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/7f76b6abaa72fe6f140232bb.mp3" }, { "key": "original-emo_Elation-nl-1-seed1702-scale0.5", "bucket": "emo_Elation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "eca81e766a5b893f2accdb92c4596545dad5ad4d77ea9e014a52717b5cc44560", "task_id": "emo_Elation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.10396939516067505, "target_z": -0.484374989629785, "ce": 6.2767791748046875, "genuineness": 4.413206577301025, "identity": 0.7187955975532532, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/973d88d14aec91b4f0a2e2c4.mp3" }, { "key": "original-emo_Elation-nl-1-seed1702-scale0.75", "bucket": "emo_Elation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "92156e4b643d6f9957318bf5822f95ad02f13db907c7ea55f9b0d37529f29fa0", "task_id": "emo_Elation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.2948102355003357, "target_z": -0.21874997925956996, "ce": 6.316492557525635, "genuineness": 4.362998008728027, "identity": 0.6378167867660522, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/824d191badb043c8ea4cf7c7.mp3" }, { "key": "original-emo_Elation-nl-1-seed1702-scale1.0", "bucket": "emo_Elation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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 Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "10a0c1cbba64ed4bf0a006bcdf27d7b7f1ab8713fda19d514683edd19655a4ba", "mp3_sha256": "eb503fbf06bcc70678e68dfd6663ecebc059c39bdb1b4136c15e38d5d6ef00c8", "task_id": "emo_Elation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Elation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Elation. 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 Elation. 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 Elation. 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": 0.3284880220890045, "target_z": -0.17187498962978498, "ce": 6.086154937744141, "genuineness": 4.143336772918701, "identity": 0.6698223948478699, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Elation/nl/2b96c1b4bc938de82b5d35a7.mp3" } ], "source_standard_audio_unchanged": true }