{ "complete": true, "report": { "bucket": "emo_Infatuation", "label": "Intense Infatuation", "definition": { "id": "emo_Infatuation", "category": "emotion", "head": "emo_Infatuation", "pole": "high", "label": "Intense Infatuation", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_infatuation/full-v2-sealed/sealed-selected", "mission": "emotion_infatuation", "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": 6.0394123792648315, "genuineness": 4.419921860694886, "wer": 0.011572201233491557, "identity": 0.5773728683590889, "voiceclap": 0.08949072539806366, "fitness": 0.556668480076109, "steering_v2": 0.45603741041750206, "raw_target": 0.1386696742475033, "target_cdf": 0.45603741041750206, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.032502241134644, "genuineness": 4.407934627532959, "wer": 0.011598118279569893, "identity": 0.5773728683590889, "fitness": 0.5544591402164242, "steering_v2": 0.45311109725223414 }, "none": { "n": 50, "ce": 6.046322517395019, "genuineness": 4.431909093856811, "wer": 0.011546284187413219, "identity": null, "fitness": 0.5588778199357939, "steering_v2": 0.45896372358277 } } } } ], "selected_wording": { "id": "manual-e0a2c5b12b00", "general": "Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.", "inline": [ "Begin at a hushed, intimate volume, as if sharing a secret only with the listener.", "Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.", "Bring the volume back down to a near whisper for the final words, sealing the private moment." ], "cfg": 3, "recipe": "P06", "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": 2.5 }, "n": 20, "target_z": 0.04062499552608455, "target_raw": 0.22042572423815726, "ce": 6.021422219276428, "genuineness": 4.510485100746155, "identity": 0.5526166088879109, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.02542506083846092, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 0.09724121028415779, "target_raw": 0.25106838941574094, "ce": 5.799920988082886, "genuineness": 4.410068476200104, "identity": 0.5303304590284824, "wer": 0.015409356725146199, "valid_fraction": 1, "identity_delta": -0.04771121069788933, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 0.04062499552608455, "target_raw": 0.22042572423815726, "ce": 6.021422219276428, "genuineness": 4.510485100746155, "identity": 0.5526166088879109, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.02542506083846092, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.20553588738199463, "target_raw": 0.08719489015638829, "ce": 6.147710704803467, "genuineness": 4.470004630088806, "identity": 0.5793087780475616, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0012671083211898803, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.2452758777326538, "target_raw": 0.06568622477352619, "ce": 6.167170238494873, "genuineness": 4.470632266998291, "identity": 0.5618651181459426, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.016176551580429077, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.27480468812376707, "target_raw": 0.04970420524477959, "ce": 6.189012598991394, "genuineness": 4.479104924201965, "identity": 0.5877492144703865, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": 0.00970754474401474, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 0.13122558549924987, "target_raw": 0.2694619156420231, "ce": 5.550223255157471, "genuineness": 4.34291490316391, "identity": 0.4051623810082674, "wer": 0.011458333333333333, "valid_fraction": 1, "identity_delta": -0.17287928871810437, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 0.10670165484213108, "target_raw": 0.2561887111514807, "ce": 5.8937437534332275, "genuineness": 4.4731427192687985, "identity": 0.5055636517703533, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.07247801795601845, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 0.09534301606105361, "target_raw": 0.2500410206615925, "ce": 5.517856884002685, "genuineness": 4.353584122657776, "identity": 0.48343838155269625, "wer": 0.02333333333333333, "valid_fraction": 0.95, "identity_delta": -0.09460328817367554, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.01860351850185669, "target_raw": 0.1883691918104887, "ce": 6.05478138923645, "genuineness": 4.471573674678803, "identity": 0.509234081208706, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.06880758851766586, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 0.09724121028415779, "target_raw": 0.25106838941574094, "ce": 5.799920988082886, "genuineness": 4.410068476200104, "identity": 0.5303304590284824, "wer": 0.015409356725146199, "valid_fraction": 1, "identity_delta": -0.04771121069788933, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 0.012527465711086042, "target_raw": 0.2052183635532856, "ce": 5.989254379272461, "genuineness": 4.494167470932007, "identity": 0.5475740596652031, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": -0.03046761006116867, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": -0.06941528499309448, "target_raw": 0.16086809597909452, "ce": 5.967213439941406, "genuineness": 4.433917438983917, "identity": 0.5486033648252487, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": -0.029438304901123046, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.08876953476675566, "target_raw": 0.15039290264248847, "ce": 6.077815151214599, "genuineness": 4.468121802806854, "identity": 0.5313073977828026, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04673427194356918, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.18495483424046902, "target_raw": 0.09833407215774059, "ce": 6.0587527513504025, "genuineness": 4.4875776171684265, "identity": 0.5678490236401558, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.010192646086215973, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.18558960024725749, "target_raw": 0.09799051471054554, "ce": 6.156050491333008, "genuineness": 4.494167423248291, "identity": 0.5490150555968285, "wer": 0.026111111111111113, "valid_fraction": 0.95, "identity_delta": -0.029026614129543306, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.19067383003394228, "target_raw": 0.09523875266313553, "ce": 6.171737289428711, "genuineness": 4.495736455917358, "identity": 0.587935808300972, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.00989413857460022, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.2218261740958258, "target_raw": 0.07837802022695542, "ce": 6.201323747634888, "genuineness": 4.468749451637268, "identity": 0.5611736312508583, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.016868038475513457, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.22470397822213595, "target_raw": 0.07682045251131057, "ce": 6.155256223678589, "genuineness": 4.479418754577637, "identity": 0.573552343994379, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.004489325731992721, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.23165893789742822, "target_raw": 0.073056186363101, "ce": 6.198940896987915, "genuineness": 4.4505489587783815, "identity": 0.5639054849743843, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.014136184751987458, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.24432983596120572, "target_raw": 0.06619825549423694, "ce": 6.1894097328186035, "genuineness": 4.500443482398987, "identity": 0.5773495078086853, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0006921619176864624, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.2499511723750891, "target_raw": 0.06315579265356064, "ce": 6.165978860855103, "genuineness": 4.3513875007629395, "identity": 0.5427157461643219, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03532592356204987, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.2696289048196376, "target_raw": 0.05250551924109459, "ce": 6.163993191719055, "genuineness": 4.427955234050751, "identity": 0.5619271323084831, "wer": 0.008596491228070175, "valid_fraction": 1, "identity_delta": -0.016114537417888642, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 0.3123413047126821, "target_raw": 0.36748804412782193, "ce": 5.664374303817749, "genuineness": 4.399399209022522, "identity": 0.4691574439406395, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.10888422578573227, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 0.2486572196661099, "target_raw": 0.33302000164985657, "ce": 5.54123809337616, "genuineness": 4.343542468547821, "identity": 0.45588033013045787, "wer": 0.023830409356725146, "valid_fraction": 0.95, "identity_delta": -0.12216133959591388, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 0.20618895996250391, "target_raw": 0.3100347019731998, "ce": 5.5095171451568605, "genuineness": 4.343856263160705, "identity": 0.44437569230794904, "wer": 0.011666666666666665, "valid_fraction": 1, "identity_delta": -0.1336659774184227, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 0.160723872774289, "target_raw": 0.2854274149984121, "ce": 5.527586603164673, "genuineness": 4.361429119110108, "identity": 0.4642083317041397, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.11383333802223206, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 0.11951294230780032, "target_raw": 0.2631226256489754, "ce": 5.687184691429138, "genuineness": 4.389985179901123, "identity": 0.5187159828841686, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.05932568684220314, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 0.09836425666982328, "target_raw": 0.2516762211918831, "ce": 5.907643437385559, "genuineness": 4.472828841209411, "identity": 0.5196362465620041, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.05840542316436768, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 0.09114989731193944, "target_raw": 0.24777155891060829, "ce": 5.5981275081634525, "genuineness": 4.399085474014282, "identity": 0.4970164645463228, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.08102520518004894, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 0.06004027638941093, "target_raw": 0.23093394972383977, "ce": 5.835365104675293, "genuineness": 4.429210460186004, "identity": 0.5075776278972626, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.07046404182910919, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 0.05419311186616732, "target_raw": 0.22776926085352897, "ce": 6.042470264434814, "genuineness": 4.501071047782898, "identity": 0.5007916241884232, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": -0.0772500455379486, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.11209716658812766, "target_raw": 0.1377671767026186, "ce": 6.063121271133423, "genuineness": 4.5227234125137326, "identity": 0.5184472516179085, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.05959441810846329, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.26967773588602195, "target_raw": 0.05247909016907215, "ce": 6.225151777267456, "genuineness": 4.439252042770386, "identity": 0.5243027232587337, "wer": 0.008333333333333333, "valid_fraction": 1, "identity_delta": -0.053738946467638014, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.31767578330412943, "target_raw": 0.026500876992940903, "ce": 6.1878211975097654, "genuineness": 4.387474751472473, "identity": 0.5780416697263717, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": -0.30432129436183136, "target_raw": 0.033728791028261186, "ce": 6.162801766395569, "genuineness": 4.305258655548096, "identity": 0.5668097503483296, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.01123191937804222, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.3057128919962121, "target_raw": 0.03297560997307301, "ce": 6.182261323928833, "genuineness": 4.330676579475403, "identity": 0.5296904876828193, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0483511820435524, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.31406249845133694, "target_raw": 0.028456512466073038, "ce": 6.166375994682312, "genuineness": 4.363939642906189, "identity": 0.5485406123101711, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.029501057416200637, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.27502929767621803, "target_raw": 0.04958263874053955, "ce": 6.275190582275391, "genuineness": 4.376303386688233, "identity": 0.6062064543366432, "wer": 0.010227743271221532, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": -0.01589599393772067, "target_raw": 0.1898345983028412, "ce": 6.059547004699707, "genuineness": 4.504334597587586, "identity": 0.5745876064896583, "wer": 0.008196875588179936, "valid_fraction": 1, "identity_delta": -0.03161884784698486, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": -0.04286377144960257, "target_raw": 0.17523869886994362, "ce": 5.868843479156494, "genuineness": 4.4070560121536255, "identity": 0.5307777586579323, "wer": 0.012811148424420736, "valid_fraction": 1, "identity_delta": -0.07542869567871094, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 0.030187994477784218, "target_raw": 0.21477685615420342, "ce": 5.879010124206543, "genuineness": 4.427013759613037, "identity": 0.5374657508730888, "wer": 0.03558876935421558, "valid_fraction": 0.98, "identity_delta": -0.06874070346355438, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.0730517659273868, "ci95_z": [ -0.13878663475989475, -0.007316897094878844 ], "language_deltas": { "en": -0.09976806534019984, "de": -0.11363525122700917, "fr": 0.02186278724326745, "nl": 0.009729002689635363, "es": -0.18344730300262777 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.010166645050048828, "delta_genuineness": -0.01995774745941162, "delta_wer": -0.02277762092979484, "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": -0.0269677775118819, "ci95_z": [ -0.09407225970889208, 0.045590821144368646 ], "language_deltas": { "en": -0.14289549935669224, "de": -0.03785399546254119, "fr": 0.10122069888230853, "nl": 0.002111820244299448, "es": -0.057421911866784046 }, "languages_improved": 2, "clear_gain": false, "delta_ce": -0.1907035255432129, "delta_genuineness": -0.09727858543395997, "delta_wer": 0.0046142728362408, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.25913330373849736, "ci95_z": [ 0.12206054669539812, 0.40941651332378826 ], "language_deltas": { "en": 0.39898680957573185, "de": 0.1712402329607695, "fr": 0.1984863353682261, "nl": 0.034667966093612716, "es": 0.4922851746941466 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.2156435775756836, "delta_genuineness": 0.12803121089935302, "delta_wer": -0.002030867683041596, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 2.5, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793035641.6245391, "example": { "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.", "sentences": [ "Tu mensaje llegó después de que me fuera.", "Lo leí dos veces... y guardé el teléfono.", "Dime cuándo podemos hablar." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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.", "language": "es", "seed": 1701, "scale": 0.0, "cfg": 2.5, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "007b66174cdd237bca1a571f7acb6fc78396ec8e8c8782c73ae868fc22cd1835", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a33471e43da82f6e2e1386d10b42fc432c12df0c5db9d62053759c944776809c", "generation_seconds_batch": 17.307141129975207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22103355824947357, "target_z": 0.041748046041518154, "ce": 6.300607204437256, "genuineness": 4.337893962860107, "identity": 0.2729947566986084, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/007b66174cdd237bca1a571f7acb6fc78396ec8e8c8782c73ae868fc22cd1835.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "017f536a697b111811973daaefe05f0dfdee11839e72954c7917a2e15812f558", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "29241644e982ef32a005f481d9875f994ab4cd72109595668cc4ce1df450496a", "generation_seconds_batch": 23.20984889206011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014502808451652527, "target_z": -0.3398437383850272, "ce": 6.125868320465088, "genuineness": 4.444586753845215, "identity": 0.6808167695999146, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/017f536a697b111811973daaefe05f0dfdee11839e72954c7917a2e15812f558.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": "01d13ece63853331bdcfe2cabc89f4773ce31f95f36de08cad4ef2a6ceffe576", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5deffad2c29c5119c3584876db8c647c88a0fdc739c977b91607067500102fae", "generation_seconds_batch": 25.172945864964277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04515868425369263, "target_z": -0.283203115320856, "ce": 6.356205940246582, "genuineness": 4.65797233581543, "identity": 0.5456503629684448, "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_Infatuation/01d13ece63853331bdcfe2cabc89f4773ce31f95f36de08cad4ef2a6ceffe576.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "01f146634aa4ab0c1e1d1f62c6d93c83dd0bc763ccc062670443afe379c25fa3", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "621cb81641a4437133db0e2a5b13b19a7464a931e28a86e44235a2834f3e593b", "generation_seconds_batch": 17.68099465209525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1233840212225914, "target_z": -0.13867187263398703, "ce": 6.24500846862793, "genuineness": 4.432034492492676, "identity": 0.2628965973854065, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/01f146634aa4ab0c1e1d1f62c6d93c83dd0bc763ccc062670443afe379c25fa3.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "96aeae05345e6067a686fe20e5c585fff8d605c39b42ac603b9e76deb5be1c02", "generation_seconds_batch": 19.31762018497102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0066391825675964355, "target_z": -0.37890625129055255, "ce": 6.117925643920898, "genuineness": 4.306513786315918, "identity": 0.7125080227851868, "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_Infatuation/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "0223f5f2bf6572513fce56a0dbdb0500ee7c794b1fde9b1c12e2dddaa75c8f8d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0aa9f826015d71f36794d192b9909eabdd89600d1399b349dd48d60df98212f", "generation_seconds_batch": 25.824514879030176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07475745677947998, "target_z": -0.22851562478490792, "ce": 5.458683967590332, "genuineness": 4.124508857727051, "identity": 0.5924922227859497, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0223f5f2bf6572513fce56a0dbdb0500ee7c794b1fde9b1c12e2dddaa75c8f8d.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": "02ed64a49ced69fee29366d0eac953a5015f3e776eb18ee3935d869bcb64714f", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "f6478c1262ed7c00e9324d8c0d64855c368ac55f591842345940982d0d8ad09a", "generation_seconds_batch": 17.643648650031537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4310317039489746, "target_z": 4.125000234020193, "ce": 5.879645347595215, "genuineness": 4.507347106933594, "identity": 0.5006535649299622, "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_Infatuation/02ed64a49ced69fee29366d0eac953a5015f3e776eb18ee3935d869bcb64714f.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "02f3665dbe20ae0a5f3363ac04cd1b48a05bd3074eca861b2fe6d547dd31ed09", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "27a733f803e545356602c52f106b2336dfec96c0e8f65577ee3b9d058eac63d8", "generation_seconds_batch": 25.824514879030176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1521899700164795, "target_z": -0.08544922461125942, "ce": 5.927301406860352, "genuineness": 4.256305694580078, "identity": 0.3314639925956726, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/02f3665dbe20ae0a5f3363ac04cd1b48a05bd3074eca861b2fe6d547dd31ed09.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": "038ead3ec98dd0f959834341c7b85665bfc36cf8028ea549fa0e4ef3ff7daae5", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73628daeb18ec79740db98056370bd580a54732fe67c86393a7c10f5a2b0caaf", "generation_seconds_batch": 20.791441719047725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02507379651069641, "target_z": -0.32031249569815823, "ce": 6.054384231567383, "genuineness": 3.860914945602417, "identity": 0.27302810549736023, "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_Infatuation/038ead3ec98dd0f959834341c7b85665bfc36cf8028ea549fa0e4ef3ff7daae5.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "03de309b54befa6b38990ebb4d9aeec9724f3a0d36d83f3c3609f81de7bd6498", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c08a6d38788f85ac61a15680fce1177210efb0630511b3fe4cb80e75ce119c8", "generation_seconds_batch": 19.218189920997247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11809852719306946, "target_z": -0.1484374939774215, "ce": 6.022613525390625, "genuineness": 4.821148872375488, "identity": 0.4885490834712982, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/03de309b54befa6b38990ebb4d9aeec9724f3a0d36d83f3c3609f81de7bd6498.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "04849a9ff2790ec8204b99aa1566c4391d638b682d6b871fd9521410a5623efe", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "215b7cb6913d488680dc9d9f0ecc03657bfca77583c95621c9e166ad9ddc8e82", "generation_seconds_batch": 18.47185286693275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10435623675584793, "target_z": -0.17382812048306615, "ce": 6.213237762451172, "genuineness": 3.9676074981689453, "identity": 0.37599730491638184, "hypothesis": "The 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_Infatuation/04849a9ff2790ec8204b99aa1566c4391d638b682d6b871fd9521410a5623efe.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "048e54706321811ce3ec836c0d9841b597d2006ca878eebebc6e11cf610d0cb4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a3c20d2b628fb3803b0e92642cbca60e4be851f8675dba6ecb82aa62deb28be2", "generation_seconds_batch": 18.78566689498257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06577211618423462, "target_z": -0.24511718244533592, "ce": 5.708878040313721, "genuineness": 4.375550270080566, "identity": 0.4350368082523346, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/048e54706321811ce3ec836c0d9841b597d2006ca878eebebc6e11cf610d0cb4.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "052147353c1fe4f0cdef86ed513ee1ea9d52f63ea948bb5c6b0dfc970ce04c9a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ed4207cc942b6e027095c72a2bf668038c1462ae89f6911ee71db99971b7a7a4", "generation_seconds_batch": 22.65012021898292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04938708245754242, "target_z": -0.27539061273975096, "ce": 6.09409761428833, "genuineness": 4.218649387359619, "identity": 0.5398154258728027, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/052147353c1fe4f0cdef86ed513ee1ea9d52f63ea948bb5c6b0dfc970ce04c9a.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "0468876d5c33e8ed18a0bc4999a5ee17e6132d36e21840b4b94dcbdefe74fe00", "generation_seconds_batch": 18.87178535910789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15853255987167358, "target_z": -0.0737304845054955, "ce": 6.515059471130371, "genuineness": 4.758388519287109, "identity": 0.6514629125595093, "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_Infatuation/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "05fb056f3858f1714b228a975d5e4acd7639219e5987d851476a93100d4dd20d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e0ffc273aa33feea5958208609c768a099b64cd7c9c05d3875af8b116fd1c962", "generation_seconds_batch": 25.745757958036847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2560499608516693, "target_z": 0.1064452960454552, "ce": 6.086154937744141, "genuineness": 4.105680465698242, "identity": 0.4339897036552429, "hypothesis": "The 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_Infatuation/05fb056f3858f1714b228a975d5e4acd7639219e5987d851476a93100d4dd20d.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "06a18986524d35b86deed56aa066be7853ed0f4c260b384dc9042d7254f62bbf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "26bb47df9a97f43edcf5d57acb34638cf0846e7d01b8cbc83fb8bfd0ddb8af23", "generation_seconds_batch": 25.179646964999847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41620051860809326, "target_z": 0.4023437865656551, "ce": 5.863759994506836, "genuineness": 4.632867813110352, "identity": 0.5599290132522583, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/06a18986524d35b86deed56aa066be7853ed0f4c260b384dc9042d7254f62bbf.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "0703dbeb30337fcd3b59b8e64359c39fa3e2282db0da975b3adabce0ca9ca4c2", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "14072e98da08ce18b2ac002fde9a05539a636136737a6e2b05fc35083f715eb3", "generation_seconds_batch": 17.68099465209525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1561540961265564, "target_z": -0.0781249982792633, "ce": 6.324435234069824, "genuineness": 4.444586753845215, "identity": 0.3583701550960541, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0703dbeb30337fcd3b59b8e64359c39fa3e2282db0da975b3adabce0ca9ca4c2.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": "077e70a341a25f634511ce87210aa3194bb4928e18468914d2b207338b47cc05", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "aa699b07ed19394786d9d0de719e1e873c1d42451bb3cd196feb359070fe1509", "generation_seconds_batch": 18.094224417000078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 5.9431867599487305, "genuineness": 4.444586753845215, "identity": 0.543340265750885, "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_Infatuation/077e70a341a25f634511ce87210aa3194bb4928e18468914d2b207338b47cc05.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "078245b4bac2daa5f9893d1ff6f547d748274018b53d2819b0e7aee81cf6d98e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9fb2b45b1e57324aaf766772ecfbd32e601e203e6fbdb690be4e6f55757e71d5", "generation_seconds_batch": 27.372013543033972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2618640065193176, "target_z": 0.11718748365300125, "ce": 6.038498878479004, "genuineness": 4.632867813110352, "identity": 0.5757650136947632, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/078245b4bac2daa5f9893d1ff6f547d748274018b53d2819b0e7aee81cf6d98e.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "0789d3d301c66173c54270f5809736292617b57518c5212271196161412f6bb6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "baac33b02cc0051c4afcc671bb33966f936907ce812c3977ebe381230beea3e1", "generation_seconds_batch": 18.270366001990624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2117178738117218, "target_z": 0.024536136186757145, "ce": 5.903473377227783, "genuineness": 4.595211505889893, "identity": 0.7411913275718689, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0789d3d301c66173c54270f5809736292617b57518c5212271196161412f6bb6.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": "07c135735ee9996012c649c7c42ad70a91386714957ad043e0f85b19dd19c077", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b58dd50373f46cf3303bee1f95ce310d08b95ef9f41079d8132d869700725d6f", "generation_seconds_batch": 17.533707518014126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.016617000102996826, "target_z": -0.33593750086036833, "ce": 5.967014789581299, "genuineness": 4.20609712600708, "identity": 0.4376904368400574, "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_Infatuation/07c135735ee9996012c649c7c42ad70a91386714957ad043e0f85b19dd19c077.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "07e4efbfb254d6348844102b72b363921dd07608ec65c057e9a5e682c540d178", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "139aa307c617f7fbd4783ed530509d2c9f417f24a6ab70c28e3c884aea2539a9", "generation_seconds_batch": 19.329856134951115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04832997918128967, "target_z": -0.27734374526797406, "ce": 6.141753673553467, "genuineness": 4.419482707977295, "identity": 0.5511371493339539, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/07e4efbfb254d6348844102b72b363921dd07608ec65c057e9a5e682c540d178.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "07f09e54952ead482509ab6c4f154fbdbd082428e640a466d9a2425d9d3bd0dc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "75c138d2ff5f3b6aeb77ec3b8509e456eb07e6da6dc4395f8018c0fa90eac0cd", "generation_seconds_batch": 23.736580012948252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06577211618423462, "target_z": -0.24511718244533592, "ce": 6.252951145172119, "genuineness": 4.595211505889893, "identity": 0.62379390001297, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/07f09e54952ead482509ab6c4f154fbdbd082428e640a466d9a2425d9d3bd0dc.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": "081b145e08a74dca58cda9d360d75b78052f47fd57fac9689280f353d911a4a7", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5239096fe165e9b32a17f101c9baa0c172d557243a89f7e5d4a230a12d5c2d9e", "generation_seconds_batch": 17.490969715057872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09801363945007324, "target_z": -0.18554687435472372, "ce": 6.086154937744141, "genuineness": 4.425758361816406, "identity": 0.4386262893676758, "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_Infatuation/081b145e08a74dca58cda9d360d75b78052f47fd57fac9689280f353d911a4a7.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "0822da39631eceb7bb87467501ef7c653fbe94c3e3f58172594b23a8aef17664", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "140802dfffef82bb7cc390d0aef7bb07bc5e54b4c5c7ec3a0aa2d6805fea15e7", "generation_seconds_batch": 17.03581111400854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1664608120918274, "target_z": -0.05908203184150324, "ce": 5.240260601043701, "genuineness": 4.482243061065674, "identity": 0.4104417562484741, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0822da39631eceb7bb87467501ef7c653fbe94c3e3f58172594b23a8aef17664.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": "086a019fcf33302b9f935002e81bbe7a185018d0c32bb4ea01b1573d9eb5d590", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "5c76474cc098c4b70908f5cda6ef1bb4077e3fcb9f2d33cb902f5bda865116a3", "generation_seconds_batch": 20.29180718306452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.027781158685684204, "target_z": -0.41796873666429046, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.6243283748626709, "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_Infatuation/086a019fcf33302b9f935002e81bbe7a185018d0c32bb4ea01b1573d9eb5d590.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": "08834439390ea1f7df857a3650f98360308de744e1778cbc6a0e55e9a2fd7b76", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e4fa40c587ee20d5e2838396416fd9a1c87af6974996e1a326c23b0c7f0f238", "generation_seconds_batch": 18.041061292984523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12866951525211334, "target_z": -0.12890625129055253, "ce": 5.5817952156066895, "genuineness": 4.457139015197754, "identity": 0.6313047409057617, "hypothesis": "Celka placela petite chest bleu Elite prend la grand bibliothèque.", "wer": 0.8571428571428571, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/08834439390ea1f7df857a3650f98360308de744e1778cbc6a0e55e9a2fd7b76.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "0888505c182b305adb3f847567c5702677e485cb5dfbc817eae80dc4feec190e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2ddbcb3ee5daf0afb4f429d6d69bac240b58ce0f246a5009a3f25c05e6517712", "generation_seconds_batch": 17.516738328966312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.268836498260498, "genuineness": 4.557555198669434, "identity": 0.5936383008956909, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0888505c182b305adb3f847567c5702677e485cb5dfbc817eae80dc4feec190e.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "08def777a070f95b7bba9200d1b5426d479e6a84ec9a12b3104b3435a65b15c1", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "37b57f6e51caa8fa6f911cd9a7a5b39ce9dc5609572372cb09dde1660150825f", "generation_seconds_batch": 17.320329534006305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07158616185188293, "target_z": -0.23437499483778987, "ce": 6.213237762451172, "genuineness": 4.557555198669434, "identity": 0.6684796810150146, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/08def777a070f95b7bba9200d1b5426d479e6a84ec9a12b3104b3435a65b15c1.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "08fbe692bfb09ca1eb83f1b45c0ea12b47f6e63c58e547712137994c17b106e1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "159e671128193823b885818d273767cf8f091841b1753619df3bd26718b34647", "generation_seconds_batch": 23.98955684597604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052558377385139465, "target_z": -0.26953124268686895, "ce": 5.462655067443848, "genuineness": 4.337893962860107, "identity": 0.6624642610549927, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/08fbe692bfb09ca1eb83f1b45c0ea12b47f6e63c58e547712137994c17b106e1.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "09e6b9b45e962deb91bed598efe8129ae6003b1574be4a7a2b7cb58587937fba", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "21f1d0c586e08d6f3301dbe0d075edd6f5562cf44296cc950c3dfeed083aeeed", "generation_seconds_batch": 17.369714931002818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6677901148796082, "target_z": 0.8671875111847887, "ce": 5.498397350311279, "genuineness": 4.262581825256348, "identity": 0.17250122129917145, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/09e6b9b45e962deb91bed598efe8129ae6003b1574be4a7a2b7cb58587937fba.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "09f189738ea7cd3c0ba386f626b08ee857c425ac47f17dc36052ef1a33fc29c1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cfbb6ae7535984495bf551f12f88185cbad8aecdff6200c58a29845f61d33479", "generation_seconds_batch": 25.16330684896093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11651287227869034, "target_z": -0.1513671927697562, "ce": 5.593709468841553, "genuineness": 4.3127899169921875, "identity": 0.48375916481018066, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/09f189738ea7cd3c0ba386f626b08ee857c425ac47f17dc36052ef1a33fc29c1.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": "0a6f80175d9d99b3ae4607ad26ae1506865b6a16c8cb55f466bf9b08264c852e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "732dfc7af931c56a7b1023164feef5f9749bfec2dc128839fc2a4a888823470e", "generation_seconds_batch": 22.651297904085368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03412376344203949, "target_z": -0.42968750430184177, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.5006404519081116, "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_Infatuation/0a6f80175d9d99b3ae4607ad26ae1506865b6a16c8cb55f466bf9b08264c852e.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "0ade350eae8a0c62dc66e20cfacca6c75b1e8a722fa7d7305c3d7fb940f85da7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0a9d225f0d03b4cd33e11c1de883ec4ed4ea74b2fb28cf033896a56dda9642c9", "generation_seconds_batch": 24.020623928983696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2637139558792114, "target_z": 0.12060549999212591, "ce": 6.070269584655762, "genuineness": 4.494794845581055, "identity": 0.7963457107543945, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0ade350eae8a0c62dc66e20cfacca6c75b1e8a722fa7d7305c3d7fb940f85da7.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "0b9f82de5c4ee95d4c76c5c556e6b610561b19f489dffe4986fa26708f41208f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "76e7b6cb3302ec37d3ea32f87dc0299e3b9b3a97a9420ad0233c5d57d1598b08", "generation_seconds_batch": 19.092525899992324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0034678876399993896, "target_z": -0.3730468812376706, "ce": 6.229123115539551, "genuineness": 4.469690799713135, "identity": 0.6449310779571533, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0b9f82de5c4ee95d4c76c5c556e6b610561b19f489dffe4986fa26708f41208f.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": "0baf05586172d8d5efcf9b29b862c59d5fc6634b4dde1c4554d4cbf61958e27d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "998cecfbc3812cd8eaddcea80861b16ec2dfdbfdedb1cbf93fecdb35e61e9c19", "generation_seconds_batch": 19.27452546497807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14452600479125977, "target_z": -0.09960937349435538, "ce": 5.756534099578857, "genuineness": 4.808597087860107, "identity": 0.748433530330658, "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_Infatuation/0baf05586172d8d5efcf9b29b862c59d5fc6634b4dde1c4554d4cbf61958e27d.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "0c52d4fad299ade25a94c4cf90b694d191a1ca61d96666301e79b798b6c39220", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0891a840c83039a418831a34bb2086958dc16167397e5315f2b750c0ed541a38", "generation_seconds_batch": 23.103686671005562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07792875170707703, "target_z": -0.22265625473202597, "ce": 5.43088436126709, "genuineness": 4.457139015197754, "identity": 0.26390138268470764, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0c52d4fad299ade25a94c4cf90b694d191a1ca61d96666301e79b798b6c39220.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "0c9c9b1b60a3915c7546ab3de6b59050b4a05c7fd033d4a007ade852238587f7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6d32511b0285a011fe3917382e65252394c9ec490457fe4a4574d779a0a7c7f8", "generation_seconds_batch": 23.99192730395589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7777284383773804, "target_z": 1.0703125232299455, "ce": 5.434855937957764, "genuineness": 4.344170093536377, "identity": 0.40160027146339417, "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_Infatuation/0c9c9b1b60a3915c7546ab3de6b59050b4a05c7fd033d4a007ade852238587f7.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "2e4d46e502ff0ddd7df8c1f09091da7cc4d96107b9aea64d0c361210aac80b6d", "generation_seconds_batch": 17.482693555997685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002874717116355896, "target_z": -0.3613281136001193, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.7610715627670288, "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_Infatuation/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "0d22bd015a6069a72253e2e3a00fd55ff37b12b4b5d9c2b9c4458c3be357c325", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d701e49a62e679f6642c9c9fdfab7bc990b485fec030295a0a12a9ec0e853eb6", "generation_seconds_batch": 23.948409872013144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11704142391681671, "target_z": -0.1503906265056446, "ce": 5.7406487464904785, "genuineness": 4.68307638168335, "identity": 0.51241135597229, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0d22bd015a6069a72253e2e3a00fd55ff37b12b4b5d9c2b9c4458c3be357c325.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "0d4b98b95c90f2ba31ce5595d44e8052ef94fda189cc0cf3abc4924e13b10cad", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e105f3b471a2b1f5850efdc660eedb3d64ccd3af8783f24404a9e3a2e13c6073", "generation_seconds_batch": 17.892526929965243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7164166569709778, "target_z": 0.9570312220380285, "ce": 4.946381568908691, "genuineness": 4.193545341491699, "identity": 0.38313281536102295, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0d4b98b95c90f2ba31ce5595d44e8052ef94fda189cc0cf3abc4924e13b10cad.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": "0d7230ca3016aa739605023e826f42f09e8501a6def7006f99c68994d1739330", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42d25480162459628605cad163257778f5f73fa04730043e07eb110c0e9bfc5e", "generation_seconds_batch": 20.653009167057462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01721017062664032, "target_z": -0.3984374939774215, "ce": 5.685050010681152, "genuineness": 4.6203155517578125, "identity": 0.7760006189346313, "hypothesis": "J'écris le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0d7230ca3016aa739605023e826f42f09e8501a6def7006f99c68994d1739330.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "0d8fad709dc2252f461732a5d8e77774d3bbb4f71f994d0d07454f83a7c5279a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3289e38a3bf049ab375763324a9fc927917ddc117ecc1091ded69d88c239a080", "generation_seconds_batch": 27.594731133896858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2935769855976105, "target_z": 0.17578123924539554, "ce": 5.8875885009765625, "genuineness": 4.093128204345703, "identity": 0.08465556055307388, "hypothesis": "The 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_Infatuation/0d8fad709dc2252f461732a5d8e77774d3bbb4f71f994d0d07454f83a7c5279a.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "0db88582277eb8a82ce2722f48191295d3264a0287fa80278e98d2b28ffc4789", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9e968cc50924873f0b69ab58a7f2d9f6bea34d1ea9b48c8d975c749d7fdd9df8", "generation_seconds_batch": 23.142438968992792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11175592988729477, "target_z": -0.16015624784907911, "ce": 6.348263263702393, "genuineness": 4.406930446624756, "identity": 0.4319969117641449, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0db88582277eb8a82ce2722f48191295d3264a0287fa80278e98d2b28ffc4789.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "0e8850e95c0ea3e5fb4a49164d6f5101c06d19967de1d5da569eb4166c542515", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d48d24f6c98d9fb4bc64b59cbb10a5f86415e463a28595d15fd7e9ece36aa386", "generation_seconds_batch": 23.367208495968953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14109042286872864, "target_z": -0.10595704732813364, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.41631603240966797, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0e8850e95c0ea3e5fb4a49164d6f5101c06d19967de1d5da569eb4166c542515.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "0f18c8762784eb0c7d1e03b992c2f42be1f60b3c81271199c8799f7adbe2117e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d783599e1e242646cce8ae8e03c6c4898c8184d6de047c2ae862c42d486a8d6b", "generation_seconds_batch": 23.779693934018724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004988908767700195, "target_z": -0.35742187607546044, "ce": 6.0305562019348145, "genuineness": 4.444586753845215, "identity": 0.5943208336830139, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0f18c8762784eb0c7d1e03b992c2f42be1f60b3c81271199c8799f7adbe2117e.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "0f8f09161e116f65501b5598ea188e3efd1b79787fa6611e962ada954a720d22", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "aa81d54431ed8601faf053dd62d33d95829d8d306f4f723d455b71a27f9d411b", "generation_seconds_batch": 27.04373802198097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23015104234218597, "target_z": 0.05859375559239431, "ce": 5.752562999725342, "genuineness": 4.419482707977295, "identity": 0.5572091937065125, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0f8f09161e116f65501b5598ea188e3efd1b79787fa6611e962ada954a720d22.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "0fc7ac390b200daeef58f0df6a37c0e5bae94c4571c5b65bc7493e0b2a39905b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6ef2598d4455b7966306521da5be1c4c175bedf2f7c11e4d18b3a6d66c050ebf", "generation_seconds_batch": 17.234122215071693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16170386970043182, "target_z": -0.06787108692082618, "ce": 6.38797664642334, "genuineness": 4.507347106933594, "identity": 0.48701104521751404, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/0fc7ac390b200daeef58f0df6a37c0e5bae94c4571c5b65bc7493e0b2a39905b.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": "1049f78d1133e3d397a116bac96c74308d913c6e6cc6fb195df16a96c4718c54", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b81099da89def2eda68ab75bdc6dda6203283d4f7b38f5dc77faf8089c181bac", "generation_seconds_batch": 23.55714846297633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05044417083263397, "target_z": -0.2734375077433152, "ce": 5.561938762664795, "genuineness": 4.331617832183838, "identity": 0.8916794657707214, "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_Infatuation/1049f78d1133e3d397a116bac96c74308d913c6e6cc6fb195df16a96c4718c54.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "10645d517e632954dcdd2b6cd531a8942fcaf8358ea74827b1272b20834cb821", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "22a29693c2b302a3cf183cb5d783e2c8737da9aa099035915d0264a7d3e5c036", "generation_seconds_batch": 18.81931687996257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 6.2767791748046875, "genuineness": 4.3881025314331055, "identity": 0.24546658992767334, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/10645d517e632954dcdd2b6cd531a8942fcaf8358ea74827b1272b20834cb821.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "11367cc12a8b2323948cf9ef8286db7f68d6a167db3e9fcf695145b2d8595f98", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dc87193a1d2ff7aef5bd084f7be0470c9d616dd47f58776a49d7475af384c3f0", "generation_seconds_batch": 25.307325784000568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08479990065097809, "target_z": -0.2099609345962568, "ce": 6.157639026641846, "genuineness": 4.570107460021973, "identity": 0.7168131470680237, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/11367cc12a8b2323948cf9ef8286db7f68d6a167db3e9fcf695145b2d8595f98.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "11897620360ff26d05576190fce93ea294dcfa2a2ccaa53c82406b58bd637a67", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cc638cabc0aa00e1d019ca262448062838d0b230245bb02c484f715164e6e3bb", "generation_seconds_batch": 19.316732804989442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017674103379249573, "target_z": -0.33398436833214523, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.6240881681442261, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/11897620360ff26d05576190fce93ea294dcfa2a2ccaa53c82406b58bd637a67.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "10ec16ea6f45144c756218da865a161357c388545b25f11a3f6e901fa4375883", "generation_seconds_batch": 17.811697938945144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5409381985664368, "target_z": 0.6328124888152113, "ce": 6.38003396987915, "genuineness": 4.256305694580078, "identity": 0.5292309522628784, "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_Infatuation/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "12b4949be6ff98ff1dccf16300ba97c915fdb7a4ecd7d4b80378a920726c0f3d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "db451d1d077e97ac95b8bc98700b7e7bfd7a03dd0a7e3f26ceff71f114f90bb7", "generation_seconds_batch": 25.675912381964736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21825867891311646, "target_z": 0.03662110412819329, "ce": 5.1469340324401855, "genuineness": 4.482243061065674, "identity": 0.6766618490219116, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de. Elle était près de la vieille fenêtre. Nous pouvons regarder en screen.", "wer": 0.42105263157894735, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/12b4949be6ff98ff1dccf16300ba97c915fdb7a4ecd7d4b80378a920726c0f3d.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "130e00937595e972bc337cde4f6d915677332dd7281f78eb77f48eed5fd9ee04", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "57b35bea16610050be63b070f4e0bac5bf712a88bade12e422fe9fca9ebe785f", "generation_seconds_batch": 24.782790525001474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1458473801612854, "target_z": -0.09716796471702334, "ce": 6.38797664642334, "genuineness": 4.65797233581543, "identity": 0.5109291672706604, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/130e00937595e972bc337cde4f6d915677332dd7281f78eb77f48eed5fd9ee04.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "13210f6707dd68db3c37f00df622626e25d47999c2bd3b51338680e140578345", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "26e3ee10ba8fff9fbab059e9782f5a9358555ac762f3754eea678c43bc5db03c", "generation_seconds_batch": 25.093255101935938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07422890514135361, "target_z": -0.22949219104901947, "ce": 6.348263263702393, "genuineness": 4.758388519287109, "identity": 0.4735315442085266, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/13210f6707dd68db3c37f00df622626e25d47999c2bd3b51338680e140578345.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "137d6aa272206c2026c0104ea9d2caea3c1e293e8b1c57762a0b38d18e2e3923", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f7231efe87292996f63899b0ba1aad16e887605fbc6791c2227e085166658e40", "generation_seconds_batch": 21.865075169014744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005582079291343689, "target_z": -0.3769531187623294, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.5168052315711975, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/137d6aa272206c2026c0104ea9d2caea3c1e293e8b1c57762a0b38d18e2e3923.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "13b01a9bfa1471afb924fc1713f8e0b2e01370335674d992593a65d4cf29be52", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "eb08424837838f4e5a5b28a0260f617023180af6530b72b716aa083726ff28a5", "generation_seconds_batch": 24.247461585095152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002874717116355896, "target_z": -0.3613281136001193, "ce": 6.109982967376709, "genuineness": 4.6203155517578125, "identity": 0.6766914129257202, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/13b01a9bfa1471afb924fc1713f8e0b2e01370335674d992593a65d4cf29be52.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "149b3f0f5bdd72fd5db829c526c17f31ebae0b564cd492abcf35456e3c3f47d2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "de345ed19fd29eb6ccbaaf89377f8009e58e86bd9e25657ea6624721ddaf7184", "generation_seconds_batch": 23.98955684597604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19242581725120544, "target_z": -0.0111083879114309, "ce": 5.285930633544922, "genuineness": 4.362998008728027, "identity": 0.7243829369544983, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/149b3f0f5bdd72fd5db829c526c17f31ebae0b564cd492abcf35456e3c3f47d2.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": "151e18e7d19f37373049721b1f685ae5b0f35f81b287ef39d0dbcd0a88e17395", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "2f5e4147cb7981c68609bcec5442486f17080e75ed7188e6e708c746cf3c68d3", "generation_seconds_batch": 19.27452546497807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010867580771446228, "target_z": -0.3867187538716576, "ce": 5.760505676269531, "genuineness": 4.68307638168335, "identity": 0.8139458894729614, "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_Infatuation/151e18e7d19f37373049721b1f685ae5b0f35f81b287ef39d0dbcd0a88e17395.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": "15401c3f44c41117dc1c6cf91a1e1497a08b20d9c0fbe3fa5784d5f2ad6c1707", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "f05c025af472e8ea3bb0da416a9d8c310a2e446b836d434e9de8df2c5658c1de", "generation_seconds_batch": 18.948122014990076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01555989682674408, "target_z": -0.3378906333885915, "ce": 5.879645347595215, "genuineness": 4.65797233581543, "identity": 0.8672199249267578, "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_Infatuation/15401c3f44c41117dc1c6cf91a1e1497a08b20d9c0fbe3fa5784d5f2ad6c1707.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "8ecb6c0e942f63647b2fc8613c8fa39a0adb4f1291609ce0588fbde02fc90cd5", "generation_seconds_batch": 20.41174220503308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.6023523807525635, "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_Infatuation/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.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": "155f1b5ee00984870eabffd469a241f2d4ef3f83ffd9e51a857845fc77e77299", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78c9e4c3aa28265b7707b1f78de1dffa50e8e7675ad0707aec6765c12c532697", "generation_seconds_batch": 17.6791376179317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35911715030670166, "target_z": 0.2968750154866304, "ce": 6.252951145172119, "genuineness": 4.432034492492676, "identity": 0.2508544325828552, "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_Infatuation/155f1b5ee00984870eabffd469a241f2d4ef3f83ffd9e51a857845fc77e77299.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "15a001bd8245f8a3d98e04a7a97489845294caebc20360f6a885b0771a003020", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d78dfde2f5ed25081ddbae3d12aae6b76ce25ad269735491f50afb5c367440e", "generation_seconds_batch": 23.65195850096643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014502808451652527, "target_z": -0.3398437383850272, "ce": 5.863759994506836, "genuineness": 4.482243061065674, "identity": 0.4830936789512634, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/15a001bd8245f8a3d98e04a7a97489845294caebc20360f6a885b0771a003020.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "15a6426fb688bb2cf45fbed7fcd49caa550ee264449d3b01f214b83098eafac0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "17a0f79e55632e7df6f03593597af460ec9ada87a6574fa5e7d5bac1ba4bbab9", "generation_seconds_batch": 25.745757958036847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2830060124397278, "target_z": 0.15625002409031397, "ce": 6.3641486167907715, "genuineness": 4.13078498840332, "identity": 0.21781766414642334, "hypothesis": "The 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_Infatuation/15a6426fb688bb2cf45fbed7fcd49caa550ee264449d3b01f214b83098eafac0.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "15ee7c93a95c0c8417e19094a6b0264b71889988cf12ce34ad498f6363397700", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7f59ce2b8d600984b09cab92be61b04b74c216e6ea372f4a4eafcb415d80fb7b", "generation_seconds_batch": 24.60680480999872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21482309699058533, "target_z": 0.030273430294415024, "ce": 5.617537498474121, "genuineness": 4.595211505889893, "identity": 0.5469875335693359, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/15ee7c93a95c0c8417e19094a6b0264b71889988cf12ce34ad498f6363397700.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "16b0982aeb8d30dcd68d10c883adb91edd0667dbab8db635b164c3a23e1e9a18", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8cc6b86ed7b2edf19856867b0c5d70ce6a1f65397516f16a00bd665ff3aed3d4", "generation_seconds_batch": 24.406904053059407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775899112224579, "target_z": -0.296874987954843, "ce": 6.356205940246582, "genuineness": 4.306513786315918, "identity": 0.6007348299026489, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/16b0982aeb8d30dcd68d10c883adb91edd0667dbab8db635b164c3a23e1e9a18.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": "16de873ec160bf7b0c840b254623f15bfdad13a42220d2f6870e1451496c2464", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f03f12df1c35bdcaa048912d9f75571a532204ffaec9ba5782c22cf4a428f5f", "generation_seconds_batch": 25.717814453993924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6699042916297913, "target_z": 0.87109372117766, "ce": 5.692992687225342, "genuineness": 4.413206577301025, "identity": 0.7680631875991821, "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_Infatuation/16de873ec160bf7b0c840b254623f15bfdad13a42220d2f6870e1451496c2464.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "16f7cbb546e2a691fc78c2d0455009e44423d7ca66f186437f4a974adbad531f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1664c353dcd6f81dff98987e4076fbc3ccaa51bdc6c7ddb834a84c1e43d17f7", "generation_seconds_batch": 25.848603095975704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43311408162117004, "target_z": 0.4335937418265006, "ce": 5.252174377441406, "genuineness": 4.149612903594971, "identity": 0.39836952090263367, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/16f7cbb546e2a691fc78c2d0455009e44423d7ca66f186437f4a974adbad531f.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": "17a6cf4b4c3339780eb950374bfa6f74154f5128eb5ff543314ca11c1b51b0dc", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd4b007f0f5f19981a739f6e427d3a613d5eb642dd0c1f83c2d1d518bc30cb77", "generation_seconds_batch": 17.705739979050122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0641864687204361, "target_z": -0.2480468674717769, "ce": 5.77639102935791, "genuineness": 4.6203155517578125, "identity": 0.5338855981826782, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/17a6cf4b4c3339780eb950374bfa6f74154f5128eb5ff543314ca11c1b51b0dc.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "17aca68b172fc526f5affb3333c2f0c8661967fed128ae93da60a6d4848e27af", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ac7943d87a0b6be9384bfc73a218d3bae660c63b54409aed63076873df181243", "generation_seconds_batch": 17.800545614096336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08162859827280045, "target_z": -0.21582031841503244, "ce": 6.022613525390625, "genuineness": 4.7458367347717285, "identity": 0.34928756952285767, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/17aca68b172fc526f5affb3333c2f0c8661967fed128ae93da60a6d4848e27af.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": "18a6d4fba507f9cca5ebc2bb54e809affcd0bcacf9b9505499fc8b9893203bd2", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "9629e9bdf09d5038e1f9693dccdceb47ea0cc1e37b0fd9e9df30853521ea651d", "generation_seconds_batch": 19.79489864804782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028245091438293457, "target_z": -0.3144531256452763, "ce": 6.229123115539551, "genuineness": 4.557555198669434, "identity": 0.4449617862701416, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/18a6d4fba507f9cca5ebc2bb54e809affcd0bcacf9b9505499fc8b9893203bd2.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "1939cf2167b1b1e39537676428c36878dded9393f597910a9700327bb465f5f0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5bb365af35b2611706a6e5be72f69b47ebf8a65687e6c9d0709fe9d937706ec3", "generation_seconds_batch": 26.251655403058976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1376548558473587, "target_z": -0.11230469363012453, "ce": 5.919358730316162, "genuineness": 4.250029563903809, "identity": 0.5363259315490723, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1939cf2167b1b1e39537676428c36878dded9393f597910a9700327bb465f5f0.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": "1945e5815bec4918b44e996ed190ce7c5eb1c3649dfb95ba84782deab5996f12", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7028138e5efd4a4524d25b80e7843f61392c90f9094629a557d5ce565de0a76", "generation_seconds_batch": 25.411017408012412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5345956087112427, "target_z": 0.6210937487094474, "ce": 5.677107334136963, "genuineness": 4.582659721374512, "identity": 0.522057056427002, "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_Infatuation/1945e5815bec4918b44e996ed190ce7c5eb1c3649dfb95ba84782deab5996f12.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "1a30776899114d8b639ec44e28683d0c1a55e2cf6251032b553590580191f5d3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dd282b4767aa38cd74cea4b7f402e5b15b59c2e41ca1817dea2b204e3b2817be", "generation_seconds_batch": 23.71982024004683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1355406641960144, "target_z": -0.11621093115478338, "ce": 6.316492557525635, "genuineness": 4.118232727050781, "identity": 0.19339415431022644, "hypothesis": "The 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_Infatuation/1a30776899114d8b639ec44e28683d0c1a55e2cf6251032b553590580191f5d3.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "1a87043a08c7d9315363ec203ce01b5df7ab819d5b43d959a5ae9c1b460809bf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "85d82ba76f556b3c3adef61e40b541b189119edcbeba14ec9cce554805894daa", "generation_seconds_batch": 22.63089609495364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02507379651069641, "target_z": -0.32031249569815823, "ce": 5.831989288330078, "genuineness": 4.394378662109375, "identity": 0.5313766002655029, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1a87043a08c7d9315363ec203ce01b5df7ab819d5b43d959a5ae9c1b460809bf.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "1a9c594e152482a4027db63134a340d962e11e3552e08957fee1ef771d8bcc40", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "63a1eb98718ff815f71ee2354f42bd36b787aa9667ef8bc12f458ce37e34dd82", "generation_seconds_batch": 26.13558955094777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08268570154905319, "target_z": -0.21386718588680934, "ce": 6.09409761428833, "genuineness": 4.821148872375488, "identity": 0.7947571277618408, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1a9c594e152482a4027db63134a340d962e11e3552e08957fee1ef771d8bcc40.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": "1ae15bdf29a9e55a94f02a335f8010552b8ed86d4e5598a4c39e89ae5d138c6b", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "af6ea596591ca14a2138a7c56c81d5f558d4a823a3a5be8405730f17ad3164cb", "generation_seconds_batch": 17.90445232798811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.070269584655762, "genuineness": 4.595211505889893, "identity": 0.7394227385520935, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1ae15bdf29a9e55a94f02a335f8010552b8ed86d4e5598a4c39e89ae5d138c6b.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "1af3a4eb4cf5b04b1253d9d7d238d81f8ce9dc7d39063dc073faa07fe45053f4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e5d30f6354e46a4df88c3dabac4db19ed1562ab341d95efb23331e901f0ab20c", "generation_seconds_batch": 23.94316853804048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.021438568830490112, "target_z": -0.40624999655852656, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.6389434337615967, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1af3a4eb4cf5b04b1253d9d7d238d81f8ce9dc7d39063dc073faa07fe45053f4.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": "1af4fdf4d80bfad7119f5b37097aaacff9c575884e5669f5f30ad521f67a8d02", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "7bbdb11f587772a3e77aa7d60d07d9a6dbe9b1958cbae75769062322f47c5dab", "generation_seconds_batch": 17.487678276957013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22592264413833618, "target_z": 0.050781253011289246, "ce": 6.229123115539551, "genuineness": 4.432034492492676, "identity": 0.20302896201610565, "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_Infatuation/1af4fdf4d80bfad7119f5b37097aaacff9c575884e5669f5f30ad521f67a8d02.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "1b968e1c1f7edae32739e1461412f1e29bba1ecaada50e518502bebce02f87ae", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4447172819aecf42ccc8355aae202f92d15db0422fcdc4f329bc9baf19f43af3", "generation_seconds_batch": 29.306264235987328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7692716121673584, "target_z": 1.0546874630041607, "ce": 5.772419452667236, "genuineness": 4.645420074462891, "identity": 0.8396816253662109, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1b968e1c1f7edae32739e1461412f1e29bba1ecaada50e518502bebce02f87ae.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "1bbc89c4cbc19f454c67ef64c8df88c0e48c5e545dad371db28ac6cc61222048", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "753d6c730c3dbf3747b7e6bcc54aa9f23312fb907a7b7e62914c01a24f73d9bd", "generation_seconds_batch": 25.12970911199227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007696285843849182, "target_z": -0.38085938381877565, "ce": 6.38797664642334, "genuineness": 4.124508857727051, "identity": 0.5389305353164673, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1bbc89c4cbc19f454c67ef64c8df88c0e48c5e545dad371db28ac6cc61222048.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": "1bf0f17a8270d63ce5196fabaaf23508509510ebe9a5bae9a2a180d7cc5d53bb", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "093a99397857637ad78c5ab140907b1b345f923dbec292ea7cc89fe38a05e430", "generation_seconds_batch": 17.927096002968028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10329913347959518, "target_z": -0.17578125301128925, "ce": 5.689021587371826, "genuineness": 4.6203155517578125, "identity": 0.6334403157234192, "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_Infatuation/1bf0f17a8270d63ce5196fabaaf23508509510ebe9a5bae9a2a180d7cc5d53bb.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": "1c4c007fc3f363967ca8ab94bb3319a8aab00ebf50be3b7b643dd156af9d1324", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae75f5db69a3213139033d2632dbdee679e22f0bd0e4eba2538c07c84cfa96a5", "generation_seconds_batch": 16.647802694002166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14241179823875427, "target_z": -0.1035156385508016, "ce": 6.070269584655762, "genuineness": 4.595211505889893, "identity": 0.5384109020233154, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1c4c007fc3f363967ca8ab94bb3319a8aab00ebf50be3b7b643dd156af9d1324.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "1c4d317a275382745ab0a79355efd6567c7b055950ead11e81e285cb0c0dac0f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "54e3f95cab51245310100581a6782f9d43cabe914ddd86d675c70f9bf12f6805", "generation_seconds_batch": 18.263117972994223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3464319705963135, "target_z": 0.27343753527510256, "ce": 6.181467056274414, "genuineness": 4.306513786315918, "identity": 0.37530317902565, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1c4d317a275382745ab0a79355efd6567c7b055950ead11e81e285cb0c0dac0f.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "1c9c797e17429429ecbe83bcddac1fb00017784be84053358b73c8bfdfe28735", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "552d1306f3677ea4d84705d7c3bf4a6e5f9cb26407a72db8e9776b3151332a31", "generation_seconds_batch": 19.48157295002602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3548887372016907, "target_z": 0.28906248537373797, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.6598103046417236, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1c9c797e17429429ecbe83bcddac1fb00017784be84053358b73c8bfdfe28735.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "1d23f19683d1e6148e7c046602f322633c4d338f492f56c485cc28b3045a40af", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "58826fb332137e753de1c4c4556d046a9653e9381a395baeafa3a6c35bc690b2", "generation_seconds_batch": 23.298536350019276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07370036095380783, "target_z": -0.23046874354723734, "ce": 5.863759994506836, "genuineness": 4.570107460021973, "identity": 0.7923464775085449, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1d23f19683d1e6148e7c046602f322633c4d338f492f56c485cc28b3045a40af.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "090f02159ba4678a8fb2bc02e492b0e708eba6563dc075b36294534871de3104", "generation_seconds_batch": 23.73282279993873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02249567210674286, "target_z": -0.40820312908674966, "ce": 6.252951145172119, "genuineness": 4.20609712600708, "identity": 0.5926100015640259, "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_Infatuation/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "1d70e4b28c5679514067189e9d51d992436dabccaef90ed52c4f7a8ff866db3b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "422b7b2f22af29a19b71d8f719a078e2f3fd7e69aae49327a7d4d14de3e03391", "generation_seconds_batch": 18.283402662025765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7185308337211609, "target_z": 0.9609374320308999, "ce": 5.927301406860352, "genuineness": 4.7332844734191895, "identity": 0.6625327467918396, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1d70e4b28c5679514067189e9d51d992436dabccaef90ed52c4f7a8ff866db3b.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "7dbc6fa0551695a1de7945bef6648900a3f869f561cc719ee5e0fb24a1749615", "generation_seconds_batch": 18.881001493078656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02507379651069641, "target_z": -0.32031249569815823, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.6013854742050171, "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_Infatuation/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "1deae2e492a9aa2138fbf0eef5466efbe7c11a1029b67557531d5fdaf80191a8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6a1243c7bfb932708900b75afde5518d6da17e04b9a5ff74195501551d75209a", "generation_seconds_batch": 24.03508071100805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010274410247802734, "target_z": -0.3476562409661323, "ce": 6.157639026641846, "genuineness": 4.808597087860107, "identity": 0.4681704044342041, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1deae2e492a9aa2138fbf0eef5466efbe7c11a1029b67557531d5fdaf80191a8.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "1e149d0e3b2ade81409a91e6f589d59cd908dd2a723a29bb238329fd8ee4901e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "41363f7611bb837c920e5abfd017b3a36975bad8617c3f548d4c1330b72bf1ea", "generation_seconds_batch": 26.038742668926716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033530592918395996, "target_z": -0.30468749053594807, "ce": 6.181467056274414, "genuineness": 4.162164688110352, "identity": 0.46537160873413086, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1e149d0e3b2ade81409a91e6f589d59cd908dd2a723a29bb238329fd8ee4901e.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "1e19b5d3c38a9e6a2a96091dc5f1268d791e3a3375eb99ba227b553780de40a1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a4608720ba8e5f34c2ab10400b72caed693937dc2820800a8f6b75ab3b46813d", "generation_seconds_batch": 24.057303398963995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09907073527574539, "target_z": -0.1835937555923943, "ce": 6.300607204437256, "genuineness": 4.7081804275512695, "identity": 0.7147990465164185, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1e19b5d3c38a9e6a2a96091dc5f1268d791e3a3375eb99ba227b553780de40a1.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "1e1c234f5746978d1085f338215322af498ecbab2c776eb0c2b3d541b7201f75", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ba04108f7b812d2261857e99289f73be06d051a15dbbe67a36f7a3378ed2b59e", "generation_seconds_batch": 22.92770827910863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 5.855817794799805, "genuineness": 4.6203155517578125, "identity": 0.5565338730812073, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1e1c234f5746978d1085f338215322af498ecbab2c776eb0c2b3d541b7201f75.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "dc9c557dcd32c396fe4f513744f8ef1f87d5ec725817e902884f0fb77f8edb72", "generation_seconds_batch": 23.73282279993873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.035180866718292236, "target_z": -0.43164063683006487, "ce": 6.300607204437256, "genuineness": 4.268857479095459, "identity": 0.6862205862998962, "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_Infatuation/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "1f135a994e0a653279a2f0e5499b5c7f35757073f9b9a388c831d2057179d1dd", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fca35a982024e2ad3efb092450340157aba5fc7e0b977e1d6edeeffef8d1b83c", "generation_seconds_batch": 26.445468649966642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1334264576435089, "target_z": -0.1201171962112296, "ce": 5.34748649597168, "genuineness": 4.406930446624756, "identity": 0.6234665513038635, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/1f135a994e0a653279a2f0e5499b5c7f35757073f9b9a388c831d2057179d1dd.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "205a26255ff4467d533312d10df98892d368f78b6f2d7074c28c99f2f9f49c3f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7231bb6fee71d89f8c69817baa87e9f5cfec62d3a2ced5cdc0b53bf6dc7d1765", "generation_seconds_batch": 23.250167937017977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022959589958190918, "target_z": -0.32421876075460443, "ce": 6.356205940246582, "genuineness": 4.482243061065674, "identity": 0.6857662796974182, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/205a26255ff4467d533312d10df98892d368f78b6f2d7074c28c99f2f9f49c3f.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "2087b8500835d0a93c54f457010d54949ea8a552e8e36263f584d97fcea465e2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "65069012300b8e48573f937db8530fae4019c3685d97e3efe19142dbd271c909", "generation_seconds_batch": 24.03543922409881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08162859827280045, "target_z": -0.21582031841503244, "ce": 6.316492557525635, "genuineness": 4.105680465698242, "identity": 0.13610929250717163, "hypothesis": "The 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_Infatuation/2087b8500835d0a93c54f457010d54949ea8a552e8e36263f584d97fcea465e2.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": "20880d2568ed27cc694b2bdfdeaa0a80dd1d5fe9fd08bb7cf8cb6e5b1c476b27", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ccfa3d5df407bfd5882ac72796199fc4b21984682219e79df41750c74a3bc467", "generation_seconds_batch": 25.592071415041573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 5.935244083404541, "genuineness": 4.645420074462891, "identity": 0.6176401376724243, "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_Infatuation/20880d2568ed27cc694b2bdfdeaa0a80dd1d5fe9fd08bb7cf8cb6e5b1c476b27.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "2180ab1c8881dd4d22522e1f1da86dd46087f1c4e65afa4e285b6d242bc1a107", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "30e78a39b9cfa960db362f4014270beefa88973ae2407579c675b591226e4892", "generation_seconds_batch": 29.542537412955426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3300468921661377, "target_z": 0.24316402238532542, "ce": 5.95112943649292, "genuineness": 4.381826400756836, "identity": 0.4510508179664612, "hypothesis": "I found the little box. It was beside the old window. We can look inside together?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2180ab1c8881dd4d22522e1f1da86dd46087f1c4e65afa4e285b6d242bc1a107.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "21a2f5cd02504f9dbcabeb01a5b44ea19cb262a2d6ca554c36c0b84660f751ba", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b227143234b8fff022ed7fa09aaf1511de107299c934a6712c7c38c826775753", "generation_seconds_batch": 17.805468457983807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47962647676467896, "target_z": 0.5195312977504437, "ce": 6.117925643920898, "genuineness": 4.068024158477783, "identity": 0.2602260708808899, "hypothesis": "The door is still open. I'd put your coat 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_Infatuation/21a2f5cd02504f9dbcabeb01a5b44ea19cb262a2d6ca554c36c0b84660f751ba.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": "21beea62e99c62b15faa19800f40f7e3a07c73ece62c6e5fdad1b07daae6f8c8", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "539360e00a600e3cf1735cb775638d74f327e296fc860a8ed08de632350836ac", "generation_seconds_batch": 24.434940524981357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18297798931598663, "target_z": -0.028564449656640067, "ce": 6.173524379730225, "genuineness": 4.306513786315918, "identity": 0.38373565673828125, "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_Infatuation/21beea62e99c62b15faa19800f40f7e3a07c73ece62c6e5fdad1b07daae6f8c8.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "21c07ecc46652fd516d112bf1a43791cc12213fef0db1fcfb21107976e3a657a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "908aa5a33e13497959ec9e060443fad56e8ff08e51c5dbb3104294c50e5b2f1b", "generation_seconds_batch": 26.041155007085763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2565785050392151, "target_z": 0.10742184854367307, "ce": 6.4515180587768555, "genuineness": 4.482243061065674, "identity": 0.26093360781669617, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/21c07ecc46652fd516d112bf1a43791cc12213fef0db1fcfb21107976e3a657a.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "221cc83cb6f27f7a18fe25d07e741f395bcc36fab4d7982e4ff034768347a1b9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d34add0ca9029815d5188768ce009f07d837bd3c3d238e2da2e3831c370f7a35", "generation_seconds_batch": 17.901691467035562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2623925805091858, "target_z": 0.11816409121479386, "ce": 6.117925643920898, "genuineness": 4.381826400756836, "identity": 0.4795825779438019, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/221cc83cb6f27f7a18fe25d07e741f395bcc36fab4d7982e4ff034768347a1b9.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "221ed4b2933d06165679f0ae617e1090cdbe0ddc9f4fa70f2563b40aa4c98d9e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d7a28fab86d3623b1f4cb38effa8979708c6a322cdeab45c9319a72b1c3c43e4", "generation_seconds_batch": 24.099292289000005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 6.157639026641846, "genuineness": 4.720732688903809, "identity": 0.6818894147872925, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/221ed4b2933d06165679f0ae617e1090cdbe0ddc9f4fa70f2563b40aa4c98d9e.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": "225391f2454a67fc8f9b15288f28effe375f5013b1206cec456cbb288dcb8a7d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d64a26260e0a8656aa6bb31c95f2c35c43b32e40a67e18989f51c03935abfd4", "generation_seconds_batch": 20.653009167057462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12655532360076904, "target_z": -0.13281248881521138, "ce": 5.7247633934021, "genuineness": 4.494794845581055, "identity": 0.6649402976036072, "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_Infatuation/225391f2454a67fc8f9b15288f28effe375f5013b1206cec456cbb288dcb8a7d.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "226ca20a73a634261eb1af1a726fbc882c7d5afa90b66893b28758426022246d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6a620ea18da9ba5694174ef8c1a36d867d8b6a29514b73851f2b341c0b4aef9b", "generation_seconds_batch": 31.104960650089197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13289791345596313, "target_z": -0.12109374870944746, "ce": 6.046441555023193, "genuineness": 4.469690799713135, "identity": 0.5269933342933655, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/226ca20a73a634261eb1af1a726fbc882c7d5afa90b66893b28758426022246d.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "22e5adfb56f687f1710be07c325b0788129e1cfca89e11c538ea6bfbe23ad93c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "19b319522bfaba0dee7c7fdd37bc2db1fc688cf0b66adb48f136ef8a2c9730e5", "generation_seconds_batch": 23.954445051960647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10224203765392303, "target_z": -0.17773437177361867, "ce": 6.086154937744141, "genuineness": 3.9927117824554443, "identity": 0.3712329566478729, "hypothesis": "The 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_Infatuation/22e5adfb56f687f1710be07c325b0788129e1cfca89e11c538ea6bfbe23ad93c.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "233731abe68b91d3504a72be8be8a573f342015cc4a374b9e8e593910b74a0fe", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d2ffa73ce8e59bc7cfbbd2db21a44b22930a5bf25bfd6c7e7a4a09223d1406c6", "generation_seconds_batch": 17.730980328982696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 5.935244083404541, "genuineness": 4.369274139404297, "identity": 0.6136791706085205, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/233731abe68b91d3504a72be8be8a573f342015cc4a374b9e8e593910b74a0fe.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "23d6062154c5f61e661f2cea8b4bf80d27afb4af24230f31a89a325f7e64402a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aa5c223ac17e89f287c8b954bff330e1fda3f0ca1f44818e7d3b7c3ca11d7571", "generation_seconds_batch": 25.731898033060133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4035153090953827, "target_z": 0.37890625129055255, "ce": 5.8875885009765625, "genuineness": 4.645420074462891, "identity": 0.8216120004653931, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/23d6062154c5f61e661f2cea8b4bf80d27afb4af24230f31a89a325f7e64402a.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "24788dfbd3e11d73b603368566e51a9d4a3812d8fe8ea690c33f41de2d4c78bc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "73dc0fb13bad31fcfdca7b64f6704f2f53a544a3effd634fc1475c8227c6829d", "generation_seconds_batch": 26.0542494780384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054672569036483765, "target_z": -0.26562500516221016, "ce": 5.998785495758057, "genuineness": 4.218649387359619, "identity": 0.34497904777526855, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/24788dfbd3e11d73b603368566e51a9d4a3812d8fe8ea690c33f41de2d4c78bc.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "24e2513146e7e9445f06e8e5b6ff37b8b4b358fac1d6d27ab5ac92a0e1dd351e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "08a4e2ffad25ce91720e5b111a995ced279fe1bf25d1a0e078b4e843394685eb", "generation_seconds_batch": 26.141676479019225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05044417083263397, "target_z": -0.2734375077433152, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.626863956451416, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/24e2513146e7e9445f06e8e5b6ff37b8b4b358fac1d6d27ab5ac92a0e1dd351e.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "252a06ff6a850f0a2c560127c0146be6143948d10da9fb42c4346c4e6d91b82c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a8bd46d85abd0d6263d70e444957467876096b7721519131ae1d58742a0be5a9", "generation_seconds_batch": 23.736580012948252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.043044477701187134, "target_z": -0.2871093803773022, "ce": 6.006728172302246, "genuineness": 4.394378662109375, "identity": 0.4563121199607849, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/252a06ff6a850f0a2c560127c0146be6143948d10da9fb42c4346c4e6d91b82c.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "25769aaea2d105e16671873f54cd543aa98de2b15ef32245ac78050823480f10", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4404fdbe26958622f40d60c70d2c6210318d8766a726722cddec7a6c756c10d0", "generation_seconds_batch": 24.03737466991879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017674103379249573, "target_z": -0.33398436833214523, "ce": 6.38797664642334, "genuineness": 4.507347106933594, "identity": 0.6408782005310059, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/25769aaea2d105e16671873f54cd543aa98de2b15ef32245ac78050823480f10.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "259a70b815ab443d48230ca325de43f790d2f8ff2ed09d2568e9538a6e14e635", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7012f00470db61dfd84f0301314d2a6f90c810be7914b2afbca1bfa095815263", "generation_seconds_batch": 23.294352906988934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2872343957424164, "target_z": 0.16406249913963164, "ce": 6.229123115539551, "genuineness": 4.494794845581055, "identity": 0.41559869050979614, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/259a70b815ab443d48230ca325de43f790d2f8ff2ed09d2568e9538a6e14e635.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": "25ef511df9e838896f770e0d4489651a1b970a390b83e50098256df9e0218914", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "533a3f928523734dc5cdf2f8e9dca9bce000bb3522885721c14fd1f8b85bac5c", "generation_seconds_batch": 18.777234026929364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2560499608516693, "target_z": 0.1064452960454552, "ce": 6.3641486167907715, "genuineness": 4.65797233581543, "identity": 0.6926018595695496, "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_Infatuation/25ef511df9e838896f770e0d4489651a1b970a390b83e50098256df9e0218914.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "261f6086a1f9eeecd747494181722af0d1888db2b52a92a6a0795f70ecfee46c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d4012abe2e5060887c923d2d40e37f300094d3ed00b1167bc09af05dbc76b00c", "generation_seconds_batch": 23.066003697924316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22010859847068787, "target_z": 0.0400390654037432, "ce": 6.125868320465088, "genuineness": 4.7332844734191895, "identity": 0.7550380825996399, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/261f6086a1f9eeecd747494181722af0d1888db2b52a92a6a0795f70ecfee46c.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "268b047b3a1697387707e1c67c033b84957cecb5f3c341b9145cc1222a7c9184", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "adfe99beeb20f2d783b67bf2d5936ba09be12440838d17d646a63354e761a0b9", "generation_seconds_batch": 24.097254652064294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.002410784363746643, "target_z": -0.37109374870944745, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.4219720959663391, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/268b047b3a1697387707e1c67c033b84957cecb5f3c341b9145cc1222a7c9184.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "f155b12b879c667375a4cafcf8de5ae51d09a173f513449e5d0d0db5748462c7", "generation_seconds_batch": 18.411073093069717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017674103379249573, "target_z": -0.33398436833214523, "ce": 6.38003396987915, "genuineness": 4.268857479095459, "identity": 0.13168634474277496, "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_Infatuation/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "26d425e25cf645cf3beccc48e7be1a06960ded53f786b2923b40ccccbad50120", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "17b9568a8ae073a55fee071e195b391c0ab9daedc1969d76686d66ab5bc5104a", "generation_seconds_batch": 17.372042556060478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09959928691387177, "target_z": -0.18261718932828275, "ce": 6.078212261199951, "genuineness": 4.6705241203308105, "identity": 0.8474400639533997, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/26d425e25cf645cf3beccc48e7be1a06960ded53f786b2923b40ccccbad50120.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "276548a33bd83c50a682a89c7b54ed8156a8a37cf49a6b743348db826b0ebc8d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f18e99a4645ee39c76dedeb19ecd842c3e02d1650a5b068a4ac89793635943e2", "generation_seconds_batch": 23.141640392015688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0805715024471283, "target_z": -0.21777343717736186, "ce": 6.117925643920898, "genuineness": 4.570107460021973, "identity": 0.788626492023468, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/276548a33bd83c50a682a89c7b54ed8156a8a37cf49a6b743348db826b0ebc8d.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "27ea5517d4849b3b65d2d6b69abdaa4f107a2f7c992bc1c9218996e7f51ca032", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2a3f72c24a155e95903511bdac0f3c0b8d511937b417ff448629c22941fc5fa4", "generation_seconds_batch": 23.873147011967376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01555989682674408, "target_z": -0.3378906333885915, "ce": 6.125868320465088, "genuineness": 4.394378662109375, "identity": 0.703741192817688, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/27ea5517d4849b3b65d2d6b69abdaa4f107a2f7c992bc1c9218996e7f51ca032.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": "2860b978b363b5be1d53174cd9d2adee33b3e87a2b259209ecbf8786714dd200", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ab1424e5694db733ae88287358e9548c290c171c966d057ff641f340cb05f6b", "generation_seconds_batch": 25.717814453993924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2375507354736328, "target_z": 0.07226562822638133, "ce": 5.613565921783447, "genuineness": 4.369274139404297, "identity": 0.7301493883132935, "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_Infatuation/2860b978b363b5be1d53174cd9d2adee33b3e87a2b259209ecbf8786714dd200.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": "28a6818d72f6f7f0a28eaf2c3f90b02d5ba501348c0bb900763f4cd524ed3b5b", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3633d925fc7a5fe658ec689d37eb54ddeaa79642f9261e46498bbf22a391a63", "generation_seconds_batch": 16.670864054001868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03881607949733734, "target_z": -0.29492188295840727, "ce": 6.260893821716309, "genuineness": 4.507347106933594, "identity": 0.6882169246673584, "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_Infatuation/28a6818d72f6f7f0a28eaf2c3f90b02d5ba501348c0bb900763f4cd524ed3b5b.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": "290dd6ee74922401bc7f9cca2d268b603ceafff8f49d7f0fa88fc7d71c571dbf", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b0cc78afdbfcc35edd63d29969e2c88be240d43417e86b881608095cbec2375b", "generation_seconds_batch": 17.39164016302675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38765883445739746, "target_z": 0.34960940102614274, "ce": 5.359400749206543, "genuineness": 4.18726921081543, "identity": 0.514549732208252, "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_Infatuation/290dd6ee74922401bc7f9cca2d268b603ceafff8f49d7f0fa88fc7d71c571dbf.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "297926faec39d67bff12bd833033c4a596d380861c39aaa905a32518f090c5ae", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "28936885d18d08fc61846c0c19d4eadbae1d4b72d327c9581e450691603ca1cc", "generation_seconds_batch": 22.63089609495364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018731191754341125, "target_z": -0.33203126333570954, "ce": 5.990842819213867, "genuineness": 4.319066047668457, "identity": 0.6081109046936035, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/297926faec39d67bff12bd833033c4a596d380861c39aaa905a32518f090c5ae.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "29b3b605a7a929280ae78697833ccd383745d0c54ce20e22e63e9b2154991c46", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "698f94e92c74c8e8b539eb0225217bbda4acc07c6d207c38682500713cecaf65", "generation_seconds_batch": 23.185560903977603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21297317743301392, "target_z": 0.02685546901886511, "ce": 5.927301406860352, "genuineness": 4.758388519287109, "identity": 0.4461545944213867, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/29b3b605a7a929280ae78697833ccd383745d0c54ce20e22e63e9b2154991c46.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "2a9db2c20ad933cc31f4d202678c378971db0d79d789b371a46cde6a47ba7eaa", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0c274e851718842f23afaac45088a0b2bc15f1bf1c80fb4227f9cbe9b614c0fe", "generation_seconds_batch": 28.635297066997737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18899023532867432, "target_z": -0.017456061745209167, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.8230578899383545, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2a9db2c20ad933cc31f4d202678c378971db0d79d789b371a46cde6a47ba7eaa.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": "2aa3bda20c0f6a57fcfcd662bec0223bce12952082dd5447461504d9d80b012d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b536b922f9f20acf83f32081a5bc6d2d5e274a063ec466c37482686651fb72e", "generation_seconds_batch": 33.189911843976006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1012165546417236, "target_z": 3.515624867503273, "ce": 5.458683967590332, "genuineness": 4.13078498840332, "identity": 0.4197099208831787, "hypothesis": "Tu mensaje llegó después de que me fuera, lo leí dos veces y guardé el teléfono, dime cuándo pudemos hablar.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2aa3bda20c0f6a57fcfcd662bec0223bce12952082dd5447461504d9d80b012d.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": "2aad22381d62bd3e537c07dd89eb04348b90f0f07d6e333c5a2b56899dba946d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7253666fb3c9f1bd8ae32a796101484622f7afaffb719ebc988e4796b5f306df", "generation_seconds_batch": 24.434940524981357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21033042669296265, "target_z": 0.021972651464201024, "ce": 6.0146708488464355, "genuineness": 4.218649387359619, "identity": 0.3797140121459961, "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_Infatuation/2aad22381d62bd3e537c07dd89eb04348b90f0f07d6e333c5a2b56899dba946d.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "2ae6335a700404d6a6441ad8ebe81ddb429aebdf82ce7edac6baf519709d304d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d3c3cf16fa554f26855c6be3085615f4051352d7eb58202335b36e6c0b90461d", "generation_seconds_batch": 23.55227124004159, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23887211084365845, "target_z": 0.07470703700371338, "ce": 6.022613525390625, "genuineness": 3.7040140628814697, "identity": 0.41463327407836914, "hypothesis": "The 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_Infatuation/2ae6335a700404d6a6441ad8ebe81ddb429aebdf82ce7edac6baf519709d304d.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "2bb99a84a30216168a3eddd749a3b209bbbca6666fdd8ffb382e70adf81c4f32", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ff0c4e6d50ce01604d8efe5af8551d8a669ed62dd8abb0c1bbcb8ff4c3e9b539", "generation_seconds_batch": 23.68701149302069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04515868425369263, "target_z": -0.283203115320856, "ce": 6.427689552307129, "genuineness": 4.557555198669434, "identity": 0.5370742082595825, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2bb99a84a30216168a3eddd749a3b209bbbca6666fdd8ffb382e70adf81c4f32.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "2d0fa07bd3a27c875e5260ee1c0a71fb496a85de750ced4a86ee33b8661e9c8f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "566b4fb9e205700588768684c0f535429f25f6800e9c5ebbb557c7a013b8c290", "generation_seconds_batch": 23.748968765023164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06524355709552765, "target_z": -0.24609376247534115, "ce": 6.252951145172119, "genuineness": 4.042920112609863, "identity": 0.21582235395908356, "hypothesis": "The 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_Infatuation/2d0fa07bd3a27c875e5260ee1c0a71fb496a85de750ced4a86ee33b8661e9c8f.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "2d1f97ec1e6263428d40218d1aba0fdbfa88c959d817b324547fbc0176770b56", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "26dc58116deb2c3d4c64693050e2b8a421abe9644aa86819cf59604c17acb18c", "generation_seconds_batch": 26.96136276505422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059958070516586304, "target_z": -0.25585937005288195, "ce": 6.086154937744141, "genuineness": 4.758388519287109, "identity": 0.7430892586708069, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2d1f97ec1e6263428d40218d1aba0fdbfa88c959d817b324547fbc0176770b56.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "2d2e49d5623033bcf23ecf4d069eec46c1b806e79115e74afc1916d612ba71d5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b05ae705ed9e3ecab5dfdc284c4a76403e4b46fab8984ed58a8d279909113b6c", "generation_seconds_batch": 19.722007630974986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4193717837333679, "target_z": 0.4082031015549623, "ce": 5.847874641418457, "genuineness": 4.256305694580078, "identity": 0.41076523065567017, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2d2e49d5623033bcf23ecf4d069eec46c1b806e79115e74afc1916d612ba71d5.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "2d630cd56251f7b9cb2055e873f4ec2423c7b0db79f05bb5ec950089101808d8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e0bbd9f5bb2734452db646fdd9b109d8a5a62f2f2794e0621b1cab62cb774892", "generation_seconds_batch": 23.5776075120084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05572967231273651, "target_z": -0.263671872633987, "ce": 6.205295085906982, "genuineness": 4.519899368286133, "identity": 0.4798630475997925, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2d630cd56251f7b9cb2055e873f4ec2423c7b0db79f05bb5ec950089101808d8.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "2d84784071d5d792f8703297c711c7ec2f2cc19e91e5f93b2fd5fcbcc872be5e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f88938cdf57ad54ffd8c2a112d1f674a337968d770d2b9d1d8fd83d6441c4239", "generation_seconds_batch": 24.287753941025585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02249567210674286, "target_z": -0.40820312908674966, "ce": 6.070269584655762, "genuineness": 4.469690799713135, "identity": 0.3976156711578369, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2d84784071d5d792f8703297c711c7ec2f2cc19e91e5f93b2fd5fcbcc872be5e.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "2d91e059f2b41bade138c153ce4611478612668a6260fa419ec25671c98d9989", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "478230b0ddb0bb2e548ff7d838fa7d3ac0450201516490447808563a8cbec9c4", "generation_seconds_batch": 25.33839057700243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05150127410888672, "target_z": -0.2714843752150921, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.5821362137794495, "hypothesis": "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_Infatuation/2d91e059f2b41bade138c153ce4611478612668a6260fa419ec25671c98d9989.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "2db44f02080b7db7a942dcfcc095b990f3c0bc2c707037b34e4e68366de38f22", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ebb185a35f7e9cff3d0bfbdb85c7af02f5ea415a80afc51b2ea79a4cde6793cc", "generation_seconds_batch": 24.172994106076658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06471501290798187, "target_z": -0.24707031497355902, "ce": 6.332377910614014, "genuineness": 4.557555198669434, "identity": 0.5795115828514099, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2db44f02080b7db7a942dcfcc095b990f3c0bc2c707037b34e4e68366de38f22.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "2de54ca376b006a7e97fde4108c94ab9836e7766972b764c591d9b8a84220480", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5c529db4b41609ca92ac064a187a881552d32173f4f794fe8487d75349593f00", "generation_seconds_batch": 22.79102186707314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 6.149696350097656, "genuineness": 4.68307638168335, "identity": 0.6501600742340088, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2de54ca376b006a7e97fde4108c94ab9836e7766972b764c591d9b8a84220480.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "2e1a2c4f7c90e98f48e4b86ad145738a149a2895321e43b31998793a9d73fd35", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb0d5598b5d572e1304da95413e586baeaff3f1e5fbbed19acccaf0fe491b39d", "generation_seconds_batch": 22.85784717905335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2238084375858307, "target_z": 0.046874987954843024, "ce": 6.006728172302246, "genuineness": 4.482243061065674, "identity": 0.8112772107124329, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2e1a2c4f7c90e98f48e4b86ad145738a149a2895321e43b31998793a9d73fd35.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "2ea8d2f3039cf3991585d873ecf4bd986aea36c19069a040caedb0ff0ccbc379", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c7dea6fec9f12a55927e791be1780c15e9749873769af94ea55b7cde88ac037d", "generation_seconds_batch": 28.635297066997737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2542000412940979, "target_z": 0.10302733476990529, "ce": 6.1894097328186035, "genuineness": 4.645420074462891, "identity": 0.6297279596328735, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/2ea8d2f3039cf3991585d873ecf4bd986aea36c19069a040caedb0ff0ccbc379.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "304bcc514f9b205797bb592a656db696dae9a0cda96fc9dacf03dd061600dfc1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "011658dfaa1ac37cd44e45c30241af825987fb90f1dcfb8de106e9617f5fb13b", "generation_seconds_batch": 23.223430457990617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014038875699043274, "target_z": -0.39257812392453956, "ce": 6.260893821716309, "genuineness": 4.369274139404297, "identity": 0.4884614944458008, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/304bcc514f9b205797bb592a656db696dae9a0cda96fc9dacf03dd061600dfc1.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "3080574647b8ed36b8cfeb083a9b558bf0a6cdb144910dc8d6e7720cd50c48b3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ce5e195fbc25736a85ea619a4308c5ac29dd6fbce3cbaafb1b5b734cd06db4f0", "generation_seconds_batch": 24.952231460949406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3110191226005554, "target_z": 0.20800780206803368, "ce": 5.9431867599487305, "genuineness": 3.898571252822876, "identity": 0.41315123438835144, "hypothesis": "The 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_Infatuation/3080574647b8ed36b8cfeb083a9b558bf0a6cdb144910dc8d6e7720cd50c48b3.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "30ae78c2d0cdb51477d419789a33f86b2ba3f1507eb954b45c3f57fa57915367", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0cd2d2e538b90df6d802835b8d0ef114e21687bc944d941a95b4a6da52c437fb", "generation_seconds_batch": 26.019405515980907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20458245277404785, "target_z": 0.011352539801879056, "ce": 5.736677646636963, "genuineness": 4.7458367347717285, "identity": 0.7264231443405151, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/30ae78c2d0cdb51477d419789a33f86b2ba3f1507eb954b45c3f57fa57915367.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "30dffcdc7e1610ad895487d68a75d83cf509cf5f1c9a07311a1fb0f295efcbdc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2d9d3d18920a777a889147340f877cb98397c583f1588c927da23e1d708bb867", "generation_seconds_batch": 26.341403366997838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06841486692428589, "target_z": -0.24023436489067182, "ce": 5.967014789581299, "genuineness": 4.406930446624756, "identity": 0.3642443120479584, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/30dffcdc7e1610ad895487d68a75d83cf509cf5f1c9a07311a1fb0f295efcbdc.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": "310cd65e3a3cf93c40f85fafd4f7fb6df8fa8ddf114beea472e7ba09276b489c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "226bdddd901ab918f39786e6a964d14b7d8d475e63f0374beb45956ea58cbdb1", "generation_seconds_batch": 16.630369925056584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08532845228910446, "target_z": -0.20898436833214523, "ce": 6.070269584655762, "genuineness": 4.369274139404297, "identity": 0.4519422948360443, "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_Infatuation/310cd65e3a3cf93c40f85fafd4f7fb6df8fa8ddf114beea472e7ba09276b489c.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "31b7c3b51da8be544204665ef69e54c155757b556390463eda57e28d6b9df184", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "943658004e386a4d08f59ceb3ea9444b7f7ec28a1dd825eb39647cd6b14a5492", "generation_seconds_batch": 23.830663322936743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08902829885482788, "target_z": -0.20214843201515173, "ce": 6.0305562019348145, "genuineness": 4.7834930419921875, "identity": 0.7067239284515381, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/31b7c3b51da8be544204665ef69e54c155757b556390463eda57e28d6b9df184.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "32230ca2877e79d2446af1c8a5653881f4a8804b43d84ec8fde2013cf49d3b90", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8178da4aed49e2589e710ea9caeadd513df3edcc929fed6ee8de3dbcae74a162", "generation_seconds_batch": 25.92829769907985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3443177342414856, "target_z": 0.2695312151550816, "ce": 6.284721851348877, "genuineness": 4.406930446624756, "identity": 0.3314647674560547, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/32230ca2877e79d2446af1c8a5653881f4a8804b43d84ec8fde2013cf49d3b90.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "325a03d3dd7c6abeefe1309467c0d1ce3bae1f057bf34978f70fbb7223521401", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f4148ece402f58b0f2bee698ee849cd64b802eaccad65c3a0092b3451fa699ac", "generation_seconds_batch": 25.787922274903394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0969565361738205, "target_z": -0.18750000688294685, "ce": 6.125868320465088, "genuineness": 4.607763767242432, "identity": 0.6970041990280151, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/325a03d3dd7c6abeefe1309467c0d1ce3bae1f057bf34978f70fbb7223521401.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "32c4491579b20142baddf2a84951f88bd022fd552185faa1824d8c3e2444508a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a0319b069b20d1e44ddf94c9662938d480b8782121d557b8e8f9d303d47863f7", "generation_seconds_batch": 22.79102186707314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007696285843849182, "target_z": -0.38085938381877565, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.6942139267921448, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/32c4491579b20142baddf2a84951f88bd022fd552185faa1824d8c3e2444508a.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "32d3eee82bb9384dee008ea32108acda2480aa554bf2711936f4447dfbe7005e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "43ea88f0421ac9a1783563b9ffd0806c36c3c85bc9120830ac78954c241955dc", "generation_seconds_batch": 19.334795356029645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45954155921936035, "target_z": 0.48242186230956674, "ce": 5.585766792297363, "genuineness": 4.507347106933594, "identity": 0.7093260288238525, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/32d3eee82bb9384dee008ea32108acda2480aa554bf2711936f4447dfbe7005e.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": "333f60f284a4ec23a8457f25fff9526b0f3593710ef9482ed35238a7fc2f600d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99768c1b8c07b765de9791c6dbada8b42dbf218742678be17a4bbf4fb9c0e6ea", "generation_seconds_batch": 26.193772151949815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4732838273048401, "target_z": 0.5078124475175303, "ce": 6.109982967376709, "genuineness": 4.231201171875, "identity": 0.4737853407859802, "hypothesis": "Escribe el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/333f60f284a4ec23a8457f25fff9526b0f3593710ef9482ed35238a7fc2f600d.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "33b163c11b9be92b93fe6a89f36b2db87feaee9a8c5b57e5da4a82bb5ba02d9f", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "104954a4d069d7d5bb298ec59aa9f69944bcd6aff8bbfe9be09a910f774c327d", "generation_seconds_batch": 18.04726831498556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019324377179145813, "target_z": -0.4023437590338677, "ce": 6.229123115539551, "genuineness": 4.457139015197754, "identity": 0.7313293814659119, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/33b163c11b9be92b93fe6a89f36b2db87feaee9a8c5b57e5da4a82bb5ba02d9f.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "27e6b8e35b16823dcdc130486312e6f4e8b4a0437814657080d9d682273ddca9", "generation_seconds_batch": 19.202172384015284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018731191754341125, "target_z": -0.33203126333570954, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.6908267736434937, "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_Infatuation/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "342143083154776ce489599c07a0ae20002dd98a35a6d5151424e152392fa7b3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "11055206957bc01e7bec783febb8f2a0ae7bc711a005c57a269ee312decc67bc", "generation_seconds_batch": 19.36441585503053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19843806326389313, "target_z": 0.0, "ce": 5.927301406860352, "genuineness": 4.118232727050781, "identity": 0.3715989589691162, "hypothesis": "The door is still open. I've put your coat 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_Infatuation/342143083154776ce489599c07a0ae20002dd98a35a6d5151424e152392fa7b3.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "3447f7ab3d583cb6f5aa6327c3029e7d56641ed76aceb7af6a34798cb062a6e1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "392888775146ea6cd10a5d26215e07819f95bbfa09b525504e41232766a10a89", "generation_seconds_batch": 27.594731133896858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3866017162799835, "target_z": 0.3476562409661323, "ce": 5.80021858215332, "genuineness": 4.118232727050781, "identity": 0.34240204095840454, "hypothesis": "The door is still open. I put your coat on the chair. Tell me w 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_Infatuation/3447f7ab3d583cb6f5aa6327c3029e7d56641ed76aceb7af6a34798cb062a6e1.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": "3473f2dbc8abd4ccca4a9801fd445bf7eeb55c2ecfe9b98b56b0521531baff28", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e392dd700ccac2d2a138953bee15597a74dfa6bdd8eb7b72f6cf76980dfa699", "generation_seconds_batch": 24.778993019019254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06471501290798187, "target_z": -0.24707031497355902, "ce": 5.760505676269531, "genuineness": 4.406930446624756, "identity": 0.33752840757369995, "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_Infatuation/3473f2dbc8abd4ccca4a9801fd445bf7eeb55c2ecfe9b98b56b0521531baff28.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "8e9c880cb76065bf99dc479a90d16baf4126b72dbc3157c5c30df56d756f099d", "generation_seconds_batch": 19.305998158990405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 6.443574905395508, "genuineness": 4.231201171875, "identity": 0.41124972701072693, "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_Infatuation/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "35431d22ff2d24c7d949b16fc6753455e31e68c1ccbb186c7e5c2350c1113ec2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f1459d93f14d73c7e5cc63e8f79421fb94e9ea62964b4de6b940f3440f5a10d7", "generation_seconds_batch": 17.286090894951485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02084539830684662, "target_z": -0.3281249982792633, "ce": 6.1020402908325195, "genuineness": 4.808597087860107, "identity": 0.5440009832382202, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/35431d22ff2d24c7d949b16fc6753455e31e68c1ccbb186c7e5c2350c1113ec2.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "35aa4ff12bebd80aceb04069c933395427cdaa1e4553ce459cb74dab9a50d092", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eb1bcd0ec345dee978086abb6cf4022bbf8e5d690f199437d322772180014b51", "generation_seconds_batch": 24.606894865981303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2523501217365265, "target_z": 0.09960937349435538, "ce": 6.300607204437256, "genuineness": 4.507347106933594, "identity": 0.32694822549819946, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/35aa4ff12bebd80aceb04069c933395427cdaa1e4553ce459cb74dab9a50d092.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "35b7b84ea891f106d4d3d940b7c30865f06623ec070753716962f22c7537a4a7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fbcf95c2ff1caf51e479c9142fb59c0e0bcb2cd192f0aec74c1233e325c329ec", "generation_seconds_batch": 25.98978556098882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08744264394044876, "target_z": -0.2050781308074864, "ce": 6.078212261199951, "genuineness": 4.582659721374512, "identity": 0.5653886795043945, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/35b7b84ea891f106d4d3d940b7c30865f06623ec070753716962f22c7537a4a7.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "3653412aca704dbea51ce0de3ba3de52a3548749978994821d2e33462ae1d6a7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6d416555a73956dcc00ba131d48fabe3147112196532c353428feb5890372051", "generation_seconds_batch": 17.54722907708492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 6.308549880981445, "genuineness": 4.632867813110352, "identity": 0.5743451714515686, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3653412aca704dbea51ce0de3ba3de52a3548749978994821d2e33462ae1d6a7.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "366c954aca66afa112e64634097bfc8533fb2f0505c5b0844cf8cc65300dd798", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "11395dfb44e440554f0ca85207380496b1f83657abe4e8c3b8431389326e81fe", "generation_seconds_batch": 19.591348323971033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008753374218940735, "target_z": -0.3828124888152114, "ce": 6.332377910614014, "genuineness": 4.337893962860107, "identity": 0.7756279706954956, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/366c954aca66afa112e64634097bfc8533fb2f0505c5b0844cf8cc65300dd798.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "36754a80759a0a122be0f07a8d0c56a051e36594e098d1d9e70da07ebb917708", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a9de7141f241c962db543fd64f0cbf2454fd5ecbe6db8ac31b467d2e4df657c5", "generation_seconds_batch": 24.258002404938452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07105760276317596, "target_z": -0.23535157486779512, "ce": 6.09409761428833, "genuineness": 4.2751336097717285, "identity": 0.5716971158981323, "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_Infatuation/36754a80759a0a122be0f07a8d0c56a051e36594e098d1d9e70da07ebb917708.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "36919669f7e1632ff2992114530e2b21c64574c610c15ae6590d6a0da5e71e3f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b9bb3bfbdf400a82af9baf63897e2e2ae35bf257b0925c692976ec8e1440cfa", "generation_seconds_batch": 23.160426275921054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20114688575267792, "target_z": 0.005004893499888166, "ce": 5.585766792297363, "genuineness": 4.482243061065674, "identity": 0.33715808391571045, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/36919669f7e1632ff2992114530e2b21c64574c610c15ae6590d6a0da5e71e3f.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "3704a035c7550f2fca9740f60e56bbd00c308386d94281988ef08a5b4c07b8ed", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1f3f67dbc928e2d67c53794cbb0cf2c8037fd7f036227574d4776b0a5ae252ae", "generation_seconds_batch": 17.957940137013793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08691409975290298, "target_z": -0.20605468330570426, "ce": 5.77639102935791, "genuineness": 4.469690799713135, "identity": 0.4387403130531311, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3704a035c7550f2fca9740f60e56bbd00c308386d94281988ef08a5b4c07b8ed.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": "3735374c5b62513a47e4b6f94f439fc5795244e480022193a541b997daa083d5", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "525b45c9ceed1ca0ed6d25f9c92d35188f3c5e3646be4469751da934d922a575", "generation_seconds_batch": 24.01421528996434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09431379288434982, "target_z": -0.19238281067171725, "ce": 6.038498878479004, "genuineness": 4.369274139404297, "identity": 0.35541170835494995, "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_Infatuation/3735374c5b62513a47e4b6f94f439fc5795244e480022193a541b997daa083d5.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "375785ae03bb30cdc2885bf3bf81d66000ac7236606e358d3647e7c0e6d20966", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1736595e048c8ccb1cd3f779c236103299bb8fce969afedf4ce04857cd4fd6f", "generation_seconds_batch": 26.445468649966642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05361546576023102, "target_z": -0.26757813769043326, "ce": 5.557967185974121, "genuineness": 4.632867813110352, "identity": 0.4349956512451172, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/375785ae03bb30cdc2885bf3bf81d66000ac7236606e358d3647e7c0e6d20966.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": "37c14af8e3ce6ae2514bf591705ec457e0ca74359663377112f7cf08ded27961", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7dd20c78fa96dfc5795c8d7fdc2479017a7924df016b8709fb15f23b265d75c3", "generation_seconds_batch": 24.648213448002934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04410158097743988, "target_z": -0.2851562478490791, "ce": 5.831989288330078, "genuineness": 4.325342178344727, "identity": 0.624487578868866, "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_Infatuation/37c14af8e3ce6ae2514bf591705ec457e0ca74359663377112f7cf08ded27961.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "37d0d98faf3e4ae953c29e1fe2a5c80703e64baba79fd91ddea939699a014e52", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c8fdea695a3d967388f228dc61685536ef9c98c1826fe3f39cbee7895d5c4217", "generation_seconds_batch": 25.76860762492288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10118493437767029, "target_z": -0.17968750430184177, "ce": 5.824047088623047, "genuineness": 4.545003414154053, "identity": 0.6752674579620361, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/37d0d98faf3e4ae953c29e1fe2a5c80703e64baba79fd91ddea939699a014e52.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "37d9d9bbd436e0d01531d5d9c6a8fed5b6b07060f934819cbb93d51228f16dca", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5910109f7bd84bcd9cf3be9da75ae5ba1fd286bd04c4dbe6912ecab8d3e6d353", "generation_seconds_batch": 23.108276992919855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.078212261199951, "genuineness": 4.444586753845215, "identity": 0.5894634127616882, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/37d9d9bbd436e0d01531d5d9c6a8fed5b6b07060f934819cbb93d51228f16dca.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "38342d86aba0e4bb4ca337d7e7fe948febb25bd27c0519cc793cb777a7566dcf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1d9b8714025ab89a711a244d2b8cf5a501d85b60111a80955d2e2c1c29679f74", "generation_seconds_batch": 23.322871427051723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059958070516586304, "target_z": -0.25585937005288195, "ce": 5.80021858215332, "genuineness": 4.344170093536377, "identity": 0.5652120113372803, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/38342d86aba0e4bb4ca337d7e7fe948febb25bd27c0519cc793cb777a7566dcf.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "383c2fada33fb911bf0a2eb1443271d2f4d1d8d72ae80635f760f5b27527c98d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0dec45089d7f068551c141816aa754f1fe5a9002e5aad0f0f01f2c4378d83980", "generation_seconds_batch": 25.326649537077174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1276124119758606, "target_z": -0.13085938381877565, "ce": 6.435632705688477, "genuineness": 4.469690799713135, "identity": 0.37751007080078125, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/383c2fada33fb911bf0a2eb1443271d2f4d1d8d72ae80635f760f5b27527c98d.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "38c40953a5097b086e03545f345dcb1775748855e80778246ae383d13924fdf7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f21fa59a897501988f35875558519a99bc25e7c9bf6821057461701e573f0db9", "generation_seconds_batch": 23.103686671005562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18872596323490143, "target_z": -0.0179443379943181, "ce": 5.839932441711426, "genuineness": 4.7834930419921875, "identity": 0.42970404028892517, "hypothesis": "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_Infatuation/38c40953a5097b086e03545f345dcb1775748855e80778246ae383d13924fdf7.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": "3a3b8c104a48173791797f7e99ef7a1462a693d361a66d0aeee97ea4bee53144", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2754d21b1031244a3b7873f137edc47b605af349baceb51eb89e63c0e5a4750", "generation_seconds_batch": 16.690426732064225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8982535600662231, "target_z": 3.140624963864529, "ce": 5.19657564163208, "genuineness": 4.15588903427124, "identity": 0.49228426814079285, "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_Infatuation/3a3b8c104a48173791797f7e99ef7a1462a693d361a66d0aeee97ea4bee53144.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "3b08dded88163c8e53cf237855e9f459f877e31bd96b3bb0f6005c7bb91f8bb2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ab0e84ea7778c23fddc3adb43d788700e75e231b82d10ac7619fdfff1a76cfa1", "generation_seconds_batch": 23.384977680980228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16143959760665894, "target_z": -0.06835936316993511, "ce": 5.967014789581299, "genuineness": 3.9048471450805664, "identity": 0.3615674674510956, "hypothesis": "The 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_Infatuation/3b08dded88163c8e53cf237855e9f459f877e31bd96b3bb0f6005c7bb91f8bb2.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "3bf6bc41a0dfdf6c404340cccc4ae486c8d79f0def11bc8214294219e87b7aaf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ff5557b8e540397209eed216370a3a26b5845fbddee72023d59ed883046170c7", "generation_seconds_batch": 24.140048130066134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198737442493439, "target_z": -0.2890625129055253, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.5842022895812988, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3bf6bc41a0dfdf6c404340cccc4ae486c8d79f0def11bc8214294219e87b7aaf.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "3c0414e664d3413a44910dd56e6b30136b15b26e6a25cf7699f15f24185d312e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b93c87eb9b693fa710ab12ab0eb30b96b783e8ac10dc0f9b9bfdaa9365a8cb09", "generation_seconds_batch": 25.817378628067672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14452600479125977, "target_z": -0.09960937349435538, "ce": 5.681078910827637, "genuineness": 4.65797233581543, "identity": 0.5337371826171875, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3c0414e664d3413a44910dd56e6b30136b15b26e6a25cf7699f15f24185d312e.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "3c0c5520a25c095e709000da225de166ee64c15d8f072a71d561d9727ae81d46", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67c8638802d607cbc6d23b2e09aa3f905e16b48a3ea5af132bf47416771ff80b", "generation_seconds_batch": 24.03508071100805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 6.268836498260498, "genuineness": 4.507347106933594, "identity": 0.5771125555038452, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3c0c5520a25c095e709000da225de166ee64c15d8f072a71d561d9727ae81d46.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": "3c148817203ad4f5ff3a449a426040e4b6535e8634958de0ccd117b9b0b11ee6", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1873d56db1fb8b0a5ae9ef9972329581202f8c4a9c79b4516bc7eb458f4758da", "generation_seconds_batch": 23.317640352994204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.028245091438293457, "target_z": -0.3144531256452763, "ce": 5.6254801750183105, "genuineness": 4.607763767242432, "identity": 0.7084883451461792, "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_Infatuation/3c148817203ad4f5ff3a449a426040e4b6535e8634958de0ccd117b9b0b11ee6.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "0a83b848ca5cea7f300102fab93c2d675ae1fe8b6e93e7397a23f79c16f09001", "generation_seconds_batch": 21.565187492989935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009217306971549988, "target_z": -0.3496093734943554, "ce": 6.09409761428833, "genuineness": 4.3881025314331055, "identity": 0.755627453327179, "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_Infatuation/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "3ca022c1cca3f371dc2b6e9e37a775ef0321ed485df013d31578396cff05d793", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "897db6f23ab4bf51cd2943142a3fa6ab270c4124b3bf02458b5d9bdc158afeba", "generation_seconds_batch": 25.817378628067672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12074127048254013, "target_z": -0.1435546901886511, "ce": 5.77639102935791, "genuineness": 4.444586753845215, "identity": 0.6141952276229858, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3ca022c1cca3f371dc2b6e9e37a775ef0321ed485df013d31578396cff05d793.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "3d1c4de85f5eb4aba8d4ae3fe16dc8688a411d066c070d101d78621d861eeb74", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1e8c2bd38e70c0b482186e5dbdbd629b49439ade333789566f2ee0ec0232bcaa", "generation_seconds_batch": 23.853357588057406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26292112469673157, "target_z": 0.11914064371301174, "ce": 6.292664527893066, "genuineness": 4.419482707977295, "identity": 0.5446383953094482, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3d1c4de85f5eb4aba8d4ae3fe16dc8688a411d066c070d101d78621d861eeb74.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "3d31edc79f2d5699f2c8f25e56731511182e14509bee6e142ca787ac43ea5d23", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "344752648424783908ebfaffb734c943d846ef8e4fc879f43c33cd74336f2250", "generation_seconds_batch": 22.532487914082594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14531883597373962, "target_z": -0.0981445172152412, "ce": 5.593709468841553, "genuineness": 4.595211505889893, "identity": 0.6740343570709229, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3d31edc79f2d5699f2c8f25e56731511182e14509bee6e142ca787ac43ea5d23.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "3d967045c77c856778fbc1f3d01f0e9bf0a1abdd54a187c34c0dd057f61f9bf2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ac7ded650f8ea9a2e11f99c17e35f8680316d86081c24ee48a383729bb7961df", "generation_seconds_batch": 22.85784717905335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17967455089092255, "target_z": -0.034667971599970177, "ce": 5.546053409576416, "genuineness": 4.595211505889893, "identity": 0.8300294876098633, "hypothesis": "J'ai trouvé la 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_Infatuation/3d967045c77c856778fbc1f3d01f0e9bf0a1abdd54a187c34c0dd057f61f9bf2.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "3db6e41d78455843a275a7792108bf759b60349e57a3da8588cec3a02619d4e3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ea31341fc48c639fdd49b9b48a0dac9d5ac63519320aa39783b692c6cf004a09", "generation_seconds_batch": 23.748968765023164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621577262878418, "target_z": -0.28125001032442026, "ce": 6.268836498260498, "genuineness": 4.017816066741943, "identity": 0.20244097709655762, "hypothesis": "The 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_Infatuation/3db6e41d78455843a275a7792108bf759b60349e57a3da8588cec3a02619d4e3.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "3e0231123c3b91ad8239b3b3b3e3783042b2a88ea2b68065160c1b3b526121bc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d77616f6c054ad24e5e6e40040d4464b960a462f476bf6976e2ef65aacdca7b", "generation_seconds_batch": 21.768069805926643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07105760276317596, "target_z": -0.23535157486779512, "ce": 6.157639026641846, "genuineness": 4.632867813110352, "identity": 0.6083270311355591, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3e0231123c3b91ad8239b3b3b3e3783042b2a88ea2b68065160c1b3b526121bc.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "3e19baf38272f98037e4b1331d9768910cb3d539bfa15de3e4ac3111383f6b87", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0653c28cdb755bea6fe7c83b03ff57f4b6c922f3ec4fcc9f6348f312f378a883", "generation_seconds_batch": 23.376298847957514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12391257286071777, "target_z": -0.13769530636987548, "ce": 6.197352409362793, "genuineness": 4.632867813110352, "identity": 0.48753780126571655, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3e19baf38272f98037e4b1331d9768910cb3d539bfa15de3e4ac3111383f6b87.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "3e7572352c43ac5765f4a59b31c3e152fb69c8c51c92447901a906184eab8364", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f8f9464ed114214f0e294401f6c7e3dc86a0e2b828f1e55b4d37598abaded677", "generation_seconds_batch": 17.807832027901895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10329913347959518, "target_z": -0.17578125301128925, "ce": 6.24500846862793, "genuineness": 4.846253395080566, "identity": 0.5806642770767212, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3e7572352c43ac5765f4a59b31c3e152fb69c8c51c92447901a906184eab8364.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "3ef3b4b6d60ba21bc667cced42adde20fe1c587e737fc2e5615eb7e922f3abf0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d92d25b1b2ae7bd057af92004d519fb82086dc44706f7eeb7159eaa05eb39b7", "generation_seconds_batch": 22.94100840506144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 6.09409761428833, "genuineness": 4.457139015197754, "identity": 0.7161480784416199, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3ef3b4b6d60ba21bc667cced42adde20fe1c587e737fc2e5615eb7e922f3abf0.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": "3fd7ed5033d8b748521de6483bfcca433cbe50fbf44e7220788e75ca558d6c7b", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d422be79a6f3951f36354f2ec78d886469b05f34732a22666b15abee967c01e", "generation_seconds_batch": 24.085700594005175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.005582079291343689, "target_z": -0.3769531187623294, "ce": 6.078212261199951, "genuineness": 4.3504462242126465, "identity": 0.42348769307136536, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel mij wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/3fd7ed5033d8b748521de6483bfcca433cbe50fbf44e7220788e75ca558d6c7b.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "416c409454a12d9e273c2842adaa5225549e0e5fcdd9a7a8f002e70915067836", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "aabf72e00c1bb6353831ac35b226865c95df5e836688da1f3cad6c9a16a97980", "generation_seconds_batch": 23.600180077017285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08110005408525467, "target_z": -0.2167968709132503, "ce": 5.561938762664795, "genuineness": 4.494794845581055, "identity": 0.32226473093032837, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/416c409454a12d9e273c2842adaa5225549e0e5fcdd9a7a8f002e70915067836.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "41b657c3f201e901cc3e3130a545fcf9ee0da8c279e1eefa2c2fe04dfad37091", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b6e2846572d10a42113c44eab87fdc323c5aacc1bc54b6af9d54cab5d20875a1", "generation_seconds_batch": 22.907625347026624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22935821115970612, "target_z": 0.057128899313280135, "ce": 5.95112943649292, "genuineness": 4.557555198669434, "identity": 0.339352548122406, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/41b657c3f201e901cc3e3130a545fcf9ee0da8c279e1eefa2c2fe04dfad37091.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "41dd4da603213d6c083b93b0580847e84ecf4c96355c44bad6721e5408032f95", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc08a6dd075c95f593ead2675714235425b72f36389ed70db348180f189d6726", "generation_seconds_batch": 28.91577992902603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05361546576023102, "target_z": -0.26757813769043326, "ce": 5.621508598327637, "genuineness": 4.344170093536377, "identity": 0.4390840530395508, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/41dd4da603213d6c083b93b0580847e84ecf4c96355c44bad6721e5408032f95.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "41ef97eee1cd6cb0398effaeaacb79225c410d0a663d3eeb75caf470ce7371ac", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd2f8070b667b7b8054220c8aea52456e4147b1084906fb72f4f7c0d75e3b7a8", "generation_seconds_batch": 25.885171959991567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022959589958190918, "target_z": -0.32421876075460443, "ce": 5.927301406860352, "genuineness": 4.250029563903809, "identity": 0.5991541147232056, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/41ef97eee1cd6cb0398effaeaacb79225c410d0a663d3eeb75caf470ce7371ac.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "427270260a54079b30fc76df9754d7a247e709d2c04f96e6c2d836d053f34a49", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "95a2f9ccfacb96b9142d1855f9b0f8c1e653c7ae5a399ee9e75af056d696a22f", "generation_seconds_batch": 25.179646964999847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23622936010360718, "target_z": 0.06982421944904929, "ce": 5.808161735534668, "genuineness": 4.532451152801514, "identity": 0.7057372331619263, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/427270260a54079b30fc76df9754d7a247e709d2c04f96e6c2d836d053f34a49.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "51cda79c0f1df6456b81a70d8a25a72992583ac311a300d7740eecf2b3d6e37a", "generation_seconds_batch": 19.202172384015284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018731191754341125, "target_z": -0.33203126333570954, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.8002665042877197, "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_Infatuation/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "436dc43e7eeeb4045866a88a7c2dc44bb2cb9fc81ccd4a500537037d258383ec", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5173313a7cde5af4ca31c6aa9498db1b459ac774a8ead89c1dd6d44bdf5088e7", "generation_seconds_batch": 24.54896349494811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.011924684047698975, "target_z": -0.3886718863998807, "ce": 6.24500846862793, "genuineness": 4.7081804275512695, "identity": 0.548373818397522, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/436dc43e7eeeb4045866a88a7c2dc44bb2cb9fc81ccd4a500537037d258383ec.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "43a136b1d068ae9b4b8a52c14672a8a7220b36a3285ec049e447fee374e19874", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3d45e12491bd1ed88fe88cd497f4653f6e65442cc2d4f723939bc93b26ffa4d4", "generation_seconds_batch": 26.215454565011896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09167104214429855, "target_z": -0.19726562822638133, "ce": 6.109982967376709, "genuineness": 4.494794845581055, "identity": 0.6513322591781616, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/43a136b1d068ae9b4b8a52c14672a8a7220b36a3285ec049e447fee374e19874.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "43cd2f80de70f527cc451d4f3a4a9af19e3ee0f3322f4f9742257041430419e3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "846c6ebe50d38e1e74da0e6ff350d57f4a1ba6658b1a134275d30fbd8b46da51", "generation_seconds_batch": 23.600180077017285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1276124119758606, "target_z": -0.13085938381877565, "ce": 5.557967185974121, "genuineness": 4.432034492492676, "identity": 0.20951291918754578, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/43cd2f80de70f527cc451d4f3a4a9af19e3ee0f3322f4f9742257041430419e3.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66ace8e4e4e869e576866d428d60f37c710f51fc82d541075610c726acb83650", "generation_seconds_batch": 18.127504483098164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05044417083263397, "target_z": -0.2734375077433152, "ce": 6.213237762451172, "genuineness": 4.507347106933594, "identity": 0.6844420433044434, "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_Infatuation/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "43e835314a2deb552d28fe95386f5e603a15d665b3177856554ee456d0531b20", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "483783c831827712e7ae91d7b43f6bb72e804cc520a33e92f2fc1ae73e1101ba", "generation_seconds_batch": 26.065680474042892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03458768129348755, "target_z": -0.3027343855395124, "ce": 6.205295085906982, "genuineness": 4.356721878051758, "identity": 0.6240092515945435, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/43e835314a2deb552d28fe95386f5e603a15d665b3177856554ee456d0531b20.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "43fd9a25ffc0aef3c20019e313a13477a1dd9956b35e9df846b1abf91b3d6bd9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "460e8e968b09d93008fd30e4a5fd0c81ec1c6cbd7b3c4aa39420663d3a73f08e", "generation_seconds_batch": 28.44411278096959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24759317934513092, "target_z": 0.09082031841503245, "ce": 6.1894097328186035, "genuineness": 4.068024158477783, "identity": 0.3264111876487732, "hypothesis": "The 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_Infatuation/43fd9a25ffc0aef3c20019e313a13477a1dd9956b35e9df846b1abf91b3d6bd9.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "4426b0770cdc4603a1243421fb76d98d34fd0cfe839904884becc76b573711a2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "57296b7b72d22dcb0ba1c10e296ea8323d535a1709ed36ee52ce8953c254a03d", "generation_seconds_batch": 26.478070206940174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 6.038498878479004, "genuineness": 4.607763767242432, "identity": 0.5842421054840088, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4426b0770cdc4603a1243421fb76d98d34fd0cfe839904884becc76b573711a2.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": "45dcac4b85caf8aec0f0b78fa59ae255de12d107577a403ed4baa5c2bf3346ad", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0edc4af3f18f8ec47bfcfa6f5bb515789b9992d786d2de67dde008d511038566", "generation_seconds_batch": 17.188717864919454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09219959378242493, "target_z": -0.19628906196226978, "ce": 6.149696350097656, "genuineness": 4.281409740447998, "identity": 0.6405867338180542, "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_Infatuation/45dcac4b85caf8aec0f0b78fa59ae255de12d107577a403ed4baa5c2bf3346ad.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "0ac9829c713780dbdf467e725020ed7b35f84d9ca9e244b878fbda58a8cd0c33", "generation_seconds_batch": 16.64575722301379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02249567210674286, "target_z": -0.40820312908674966, "ce": 6.3641486167907715, "genuineness": 4.2374773025512695, "identity": 0.6636700630187988, "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_Infatuation/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "4600319c6bc9710c1582fabe21bd3991036b859b1d1a404ccb19d9aca0472acc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cbc60be76c260b834c0428abe5d2aa8c636963346cf4b815b4f67229c96aa16", "generation_seconds_batch": 23.99192730395589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17610684037208557, "target_z": -0.04125976979240922, "ce": 5.637393951416016, "genuineness": 4.149612903594971, "identity": 0.37669992446899414, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4600319c6bc9710c1582fabe21bd3991036b859b1d1a404ccb19d9aca0472acc.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "46b1e2a6a29494e8966a112acbb7dca58b58554a498406bd642f862c897ca27c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "36075f7e45f04a106768d6ad5b07e73ffd421223cd573263fa4d6027f6480b27", "generation_seconds_batch": 26.155632229987532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46376997232437134, "target_z": 0.4902343924224592, "ce": 5.148920059204102, "genuineness": 4.356721878051758, "identity": 0.43325498700141907, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/46b1e2a6a29494e8966a112acbb7dca58b58554a498406bd642f862c897ca27c.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": "46c10f49eee35954cdd1a8d29163e1c93a138969f9a14f497f0fa61af692f870", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5eca90168805fd88cbc9aa62ae8d5ae3af60bf5a508b545c138faea5e30fba49", "generation_seconds_batch": 23.724474738002755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05784386396408081, "target_z": -0.25976563510932815, "ce": 5.919358730316162, "genuineness": 4.344170093536377, "identity": 0.26405054330825806, "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_Infatuation/46c10f49eee35954cdd1a8d29163e1c93a138969f9a14f497f0fa61af692f870.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": "46d31f507f12433f19f302f9ec906a96e827284b2ded94a9ef7c7b61c9d92dd7", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f2850b1ea9852baa326868f05c612f8d5be8da56edec01c7d466ba01c9c80cc", "generation_seconds_batch": 16.699276280007325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003931805491447449, "target_z": -0.35937500860368354, "ce": 5.561938762664795, "genuineness": 4.080576419830322, "identity": 0.5551742911338806, "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_Infatuation/46d31f507f12433f19f302f9ec906a96e827284b2ded94a9ef7c7b61c9d92dd7.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "4776e0aad764bcd093ce2b29ed565eb793e4ef3f5268da587d3a39f1f7024e6f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "321cfd98f4bf3f376a3be22e5d12ac37b32413d2737a20cd1e6f9dc2c1a7b1dd", "generation_seconds_batch": 17.687529076007195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1334264576435089, "target_z": -0.1201171962112296, "ce": 6.125868320465088, "genuineness": 4.557555198669434, "identity": 0.5329367518424988, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4776e0aad764bcd093ce2b29ed565eb793e4ef3f5268da587d3a39f1f7024e6f.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "da7844cd9c63155028b92332753de6a700ae4610c69752037672691b5641ef32", "generation_seconds_batch": 16.812042430974543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009217306971549988, "target_z": -0.3496093734943554, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.7691555023193359, "hypothesis": "Quelqu'un déplacez la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "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_Infatuation/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.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": "498606b361da0aa01d50e77de8689b69414a3febba89c0112ac6566d4bbf671d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "107521d8e15a04f5b82326cdeb4cd554b2bce27f6100e0b0d2cf7da7574da8b0", "generation_seconds_batch": 16.690426732064225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.033562421798706, "target_z": 3.3906252667141903, "ce": 5.561938762664795, "genuineness": 4.268857479095459, "identity": 0.3722616136074066, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guarda el teléfono. Dime cuándo podemos hablar.", "wer": 0.05, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/498606b361da0aa01d50e77de8689b69414a3febba89c0112ac6566d4bbf671d.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "49cc0e37a7e512b712a9b24f84a8e7397624e0282e20603fe9a2a9fb0d308ae9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "17e0d0ccd55b0bfeb21f6f7074b2b3191d05e55d7a765ff92d3b7dd5340c17e2", "generation_seconds_batch": 23.212775830063038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05209444463253021, "target_z": -0.4628906196226978, "ce": 6.149696350097656, "genuineness": 4.6956281661987305, "identity": 0.6279042959213257, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/49cc0e37a7e512b712a9b24f84a8e7397624e0282e20603fe9a2a9fb0d308ae9.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b31cfb772b666cfa0c8b8a3cb9d6763270f05c6d5b27ec4f900da04e6b2080dc", "generation_seconds_batch": 17.811697938945144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6191635727882385, "target_z": 0.7773438003315488, "ce": 6.252951145172119, "genuineness": 4.356721878051758, "identity": 0.6124559640884399, "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_Infatuation/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "4a3813cfd3d02536aa421bd910ecb9c325ce9dc00362ea90cad92b6ffc0c2ae8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "20c3e9489278e4ef573e4a57eacb2a620672c751a8638c12df96ed1b2532f644", "generation_seconds_batch": 26.84728305891622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09325668960809708, "target_z": -0.19433594319994035, "ce": 6.0146708488464355, "genuineness": 4.519899368286133, "identity": 0.5897012948989868, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4a3813cfd3d02536aa421bd910ecb9c325ce9dc00362ea90cad92b6ffc0c2ae8.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "4a3d3257206632c865ec85f9cfe7a57cfb4a24c524cd7a32cf793d0b080b5330", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3795e5e0dc65a22248eb7cc61a7a48577cbd02e3c290fa5c4425f7976d674f2e", "generation_seconds_batch": 28.504754918045364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.471169650554657, "target_z": 0.5039062375246588, "ce": 6.0305562019348145, "genuineness": 4.6705241203308105, "identity": 0.6084709167480469, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4a3d3257206632c865ec85f9cfe7a57cfb4a24c524cd7a32cf793d0b080b5330.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "4a8659b2e444c100169675577588291c23410f18f9d747faf6b54da923ca018a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dfdd78b043a5084b428c3e3bd69bb8374994b0f2c637a74cf2b8ff2669bfd6fe", "generation_seconds_batch": 23.250167937017977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03458768129348755, "target_z": -0.3027343855395124, "ce": 6.372091293334961, "genuineness": 4.532451152801514, "identity": 0.4500931203365326, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4a8659b2e444c100169675577588291c23410f18f9d747faf6b54da923ca018a.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": "4b647ea0fc71eddee92b56e5aa2690e55249299cef354d8eb981752106359470", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41424ed6323f4227370ae8eb2bdc0850bbbbef6985e93cbcb20df97aacc318eb", "generation_seconds_batch": 16.597423230996355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05784386396408081, "target_z": -0.25976563510932815, "ce": 5.855817794799805, "genuineness": 4.406930446624756, "identity": 0.31263455748558044, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten wijk. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4b647ea0fc71eddee92b56e5aa2690e55249299cef354d8eb981752106359470.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "4b7bf855f072602b8d5aa2e9d95e9965ee3f909c992232bf68ada732af7a755e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4d0293dfff9e62647a631ebac6042c37d5cf00f6b9b07fc124ae57044693f8f0", "generation_seconds_batch": 23.223430457990617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.032009556889534, "target_z": -0.42578123924539557, "ce": 6.284721851348877, "genuineness": 4.821148872375488, "identity": 0.541161060333252, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4b7bf855f072602b8d5aa2e9d95e9965ee3f909c992232bf68ada732af7a755e.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": "4b8d5ef842892494f4f38521db991457003f55758a8aa884643d78f1d6c3fe07", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "12056c05fadb31258f78e055da42991a085c5b14e758fe7b949b90bff13c5e56", "generation_seconds_batch": 23.739534029969946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03987318277359009, "target_z": -0.29296875043018417, "ce": 6.165581703186035, "genuineness": 4.243753433227539, "identity": 0.39637094736099243, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4b8d5ef842892494f4f38521db991457003f55758a8aa884643d78f1d6c3fe07.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "4ba01266ad1e96b3f28ad97e2d707a4e521385e4b9982e8f9c946e4de11288b9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1183e60616f6a08086e5e75170d4a8edd9d15f2e98b29f3acf20dad74cfb6b6e", "generation_seconds_batch": 25.0020321670454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07370036095380783, "target_z": -0.23046874354723734, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.565697193145752, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4ba01266ad1e96b3f28ad97e2d707a4e521385e4b9982e8f9c946e4de11288b9.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "4bab059e64e2278fb87070f334683af2d26a2550ef4a1ef87819cb81cca86176", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "69a0e99c7aca8a2a708aca115e42b9ff8f5f1df6f5a079965b4b0f99769c1cc5", "generation_seconds_batch": 23.21542852197308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17201058566570282, "target_z": -0.04882812048306613, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.531977653503418, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4bab059e64e2278fb87070f334683af2d26a2550ef4a1ef87819cb81cca86176.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "4bb8b0d00c39e0263cc2c462a6371562145ca44268c2e5ed09635ff9aeef03a1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e81572137eb2767b41fc8ede0fb0a03d3efbaf55f14041e4927f0d01f4242863", "generation_seconds_batch": 17.383835167973302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2830060124397278, "target_z": 0.15625002409031397, "ce": 5.748591423034668, "genuineness": 4.331617832183838, "identity": 0.42421403527259827, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4bb8b0d00c39e0263cc2c462a6371562145ca44268c2e5ed09635ff9aeef03a1.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "4bd830ecb142b63487fb3b111d649eea41c8ddc51d92a40203d3c7d99dbec98b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8adb08b6da962a9f510dd76e16efc2bc1af1906520e0a035ebfae4ebef59ff56", "generation_seconds_batch": 23.798470308072865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07740020751953125, "target_z": -0.2236328072302438, "ce": 6.268836498260498, "genuineness": 4.381826400756836, "identity": 0.40050214529037476, "hypothesis": "The 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_Infatuation/4bd830ecb142b63487fb3b111d649eea41c8ddc51d92a40203d3c7d99dbec98b.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "4cb39ca1cc688807656b858dab3eba2b36601f198b8939ab960d2c770d454ec8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "147d8d795a008a9283d65fd4beb66121dc6cf72708954467eac4faac0c7738b2", "generation_seconds_batch": 17.67698481096886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.665675938129425, "target_z": 0.8632813011919171, "ce": 4.658459663391113, "genuineness": 4.18099308013916, "identity": 0.44042524695396423, "hypothesis": "La puerta sí queda abierta, he dejado 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_Infatuation/4cb39ca1cc688807656b858dab3eba2b36601f198b8939ab960d2c770d454ec8.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "4d1ea670269ee73aa4f0c0dc278332921c384f9c3570bdd742678e0a1cea9c82", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fea14ef6049734ce357cf6562605b0f6f745039063269bb87341c9fbde724e2a", "generation_seconds_batch": 24.17347156209871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7185308337211609, "target_z": 0.9609374320308999, "ce": 5.577824115753174, "genuineness": 4.306513786315918, "identity": 0.3968769311904907, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4d1ea670269ee73aa4f0c0dc278332921c384f9c3570bdd742678e0a1cea9c82.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "4d6c08d2bac0f5e8618d585260362bc86bb7ccf5adf67a39ec6d863a993d5f47", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "29d3a17c383c01d20409aa44b1249cc91e2e2b28518292b792137537ec81d5b5", "generation_seconds_batch": 23.055694174952805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12232691794633865, "target_z": -0.14062500516221013, "ce": 5.11317777633667, "genuineness": 4.406930446624756, "identity": 0.48923927545547485, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4d6c08d2bac0f5e8618d585260362bc86bb7ccf5adf67a39ec6d863a993d5f47.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "4e20c6c508af56fd90e7099b7ccccb6e9fd2e66519288a0846cb029c49f7fc31", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3bfc324d155c645171d816a389463a55d72a4477873f9cb804a33716849e774", "generation_seconds_batch": 25.832880217931233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1776924878358841, "target_z": -0.03833008476596824, "ce": 5.252174377441406, "genuineness": 4.482243061065674, "identity": 0.24870121479034424, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4e20c6c508af56fd90e7099b7ccccb6e9fd2e66519288a0846cb029c49f7fc31.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "4ec1fd6cdb3538fa0fb3f0109d77a192b533384327de1e4335319849bca88652", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ef0678ae48afd6903641e54efb09a674713e8b7551b32ddeb10a62db820370c8", "generation_seconds_batch": 26.238299524993636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10647043585777283, "target_z": -0.1699218691925136, "ce": 5.764476776123047, "genuineness": 4.7458367347717285, "identity": 0.666459858417511, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4ec1fd6cdb3538fa0fb3f0109d77a192b533384327de1e4335319849bca88652.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "4f7c3294724b72bbee779abcfd94b8ba7391ed51d9a04c1ec219bb11bb740bf3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "99ad295edfb2003461446836494e26ca399dc71c4949905561bd380ec5425fda", "generation_seconds_batch": 24.527209465042688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3379751443862915, "target_z": 0.2578124750493177, "ce": 5.315715789794922, "genuineness": 4.494794845581055, "identity": 0.6868531703948975, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4f7c3294724b72bbee779abcfd94b8ba7391ed51d9a04c1ec219bb11bb740bf3.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "4f8f318901106356d29a5d387dce362ce4eccade1ff7e2f202c10c71f50bc8d6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "31a061da46160b003374f03c98a08be3200f345af9f987b7e12f737bb3275ba3", "generation_seconds_batch": 23.779693934018724, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02249567210674286, "target_z": -0.40820312908674966, "ce": 6.117925643920898, "genuineness": 4.6203155517578125, "identity": 0.6680550575256348, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4f8f318901106356d29a5d387dce362ce4eccade1ff7e2f202c10c71f50bc8d6.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "4fdae178a334229c37478e9da180f658896457a3759137e6d6fcbbdc22a54637", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "dbaf1b7ee2f80959b80f3c278d6cbc42d5750b59f63e2d7e873c9b057534071a", "generation_seconds_batch": 23.987548931967467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008160203695297241, "target_z": -0.3515625060225785, "ce": 6.181467056274414, "genuineness": 4.595211505889893, "identity": 0.49503564834594727, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4fdae178a334229c37478e9da180f658896457a3759137e6d6fcbbdc22a54637.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "4fe9caaef7c635214ba6167a5cc417f0b192606bfd56d607658c442c25b51f26", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "083f30a09d7356d4ddc7cf2a6bcf765d36fe4f72fc20c8f2d2f7f4aae2822e6c", "generation_seconds_batch": 23.568827050039545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4775122404098511, "target_z": 0.5156249776304228, "ce": 5.208489894866943, "genuineness": 4.582659721374512, "identity": 0.7275810241699219, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/4fe9caaef7c635214ba6167a5cc417f0b192606bfd56d607658c442c25b51f26.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "501335fdf8fffa178545cf4f64bf1bcbc1c717025dcd67c8a8773eb80fba63e1", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1e76dd7c58058b447aacc1f22b60882685f6c522c97a4c626ddd731c88fccc8d", "generation_seconds_batch": 17.564126571058296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12708386778831482, "target_z": -0.1318359363169935, "ce": 6.292664527893066, "genuineness": 4.959221839904785, "identity": 0.6243510842323303, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/501335fdf8fffa178545cf4f64bf1bcbc1c717025dcd67c8a8773eb80fba63e1.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "502e8303e3660517f5b697a4b15128ceaa1885c2f00c2ba43b60ca7a11eb7f22", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "781637736be1ecb334d04bbaefdb73836c2edd4775713717ad7ac5971ef4e5d8", "generation_seconds_batch": 18.249701819964685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.047272875905036926, "target_z": -0.27929687779619716, "ce": 6.070269584655762, "genuineness": 4.243753433227539, "identity": 0.6382430791854858, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/502e8303e3660517f5b697a4b15128ceaa1885c2f00c2ba43b60ca7a11eb7f22.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "5121bc73aadbd0cf6b40ba6ed944869b6a635d8fe86146b207de473e6b8592e4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "96d5654269ffe42593b74d1d7a982db4b6c00d8107eb92c436960491ba25299e", "generation_seconds_batch": 25.712445350014605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059958070516586304, "target_z": -0.25585937005288195, "ce": 5.7684478759765625, "genuineness": 4.111956596374512, "identity": 0.45389389991760254, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5121bc73aadbd0cf6b40ba6ed944869b6a635d8fe86146b207de473e6b8592e4.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "5183c5cfea05dcbd13f06f67d5681963759dbd61cd92887814946f4188fc1491", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3e52e707ce56264e5d0a6d8853f3a3ab0bf8b85b912c653666ca5348ce4ae81a", "generation_seconds_batch": 23.589804211980663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621577262878418, "target_z": -0.28125001032442026, "ce": 5.045665264129639, "genuineness": 4.243753433227539, "identity": 0.2521445155143738, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5183c5cfea05dcbd13f06f67d5681963759dbd61cd92887814946f4188fc1491.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "518d5f12c25f08732462e472b593d3af84d7e6507d15dd307696e40126d3760f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d464e79bb9df0dc55de49fb092e78367f585b7cef8352f2bc7e667291006d6d1", "generation_seconds_batch": 23.790547863929532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29621973633766174, "target_z": 0.18066405680005965, "ce": 5.9431867599487305, "genuineness": 4.770940780639648, "identity": 0.4483431875705719, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/518d5f12c25f08732462e472b593d3af84d7e6507d15dd307696e40126d3760f.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "51f65859286a9c90a8446804efb5c6fba2a7261e4ceb81f3a0dc87faa4f5b6ab", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a01514d2ca90ebd272cfa54f65475c2619c3cc01fc56128336b1dc75393adc35", "generation_seconds_batch": 23.354029395035468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.047272875905036926, "target_z": -0.27929687779619716, "ce": 5.831989288330078, "genuineness": 4.545003414154053, "identity": 0.7202394604682922, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/51f65859286a9c90a8446804efb5c6fba2a7261e4ceb81f3a0dc87faa4f5b6ab.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": "52729c5f93160a78e5bd3747d23391fa0e33637f5a91aefc66518de57713737b", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "cd0801812f7c71af41bc4b271c724df28b37c2c511923473fe1853eb70866533", "generation_seconds_batch": 18.38524438405875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08744264394044876, "target_z": -0.2050781308074864, "ce": 6.23706579208374, "genuineness": 4.632867813110352, "identity": 0.700042188167572, "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_Infatuation/52729c5f93160a78e5bd3747d23391fa0e33637f5a91aefc66518de57713737b.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "52991c41502cf02f67488f828156b0e99b2fc05d8f52bfe2b31154475ddc5f38", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8fd3582c280911401028d0cd56e041a8677dbf385d2185b770e5c1bc82ee58ed", "generation_seconds_batch": 19.591348323971033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0007605105638504028, "target_z": -0.3652343786565655, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.6741341352462769, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/52991c41502cf02f67488f828156b0e99b2fc05d8f52bfe2b31154475ddc5f38.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "535225659bb0da4a7f6ccf17fa5d8b11164f958ffa47a4186338bf1d80e08308", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2173714e6d3450d0fa10d175fdb86b7a79d6ed9d5d09b4c1d805282236897ab0", "generation_seconds_batch": 25.127563854912296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006046012043952942, "target_z": -0.35546874354723734, "ce": 6.165581703186035, "genuineness": 4.519899368286133, "identity": 0.7216948866844177, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/535225659bb0da4a7f6ccf17fa5d8b11164f958ffa47a4186338bf1d80e08308.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "539e753f6a730d2e5edeb7e4a28dc65a2eae1a29b99ea16680e44d479fd964bd", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ccf593081c48db82e68c415fd3d0d1eb9f8dcdfa0e2de97c4ceceb016eaeadad", "generation_seconds_batch": 23.95335117506329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3992869257926941, "target_z": 0.37109377624123485, "ce": 5.95112943649292, "genuineness": 4.6956281661987305, "identity": 0.44149133563041687, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/539e753f6a730d2e5edeb7e4a28dc65a2eae1a29b99ea16680e44d479fd964bd.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "5403b539628d5cebbc2c89f287a9ed489bb0ba692e49c478701a8503aadd6709", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "98430345a512e8033fb85b84951d7a745b196ca2e270c180c65f2d5e723a962b", "generation_seconds_batch": 25.093255101935938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03247348964214325, "target_z": -0.3066406230641712, "ce": 6.3641486167907715, "genuineness": 4.394378662109375, "identity": 0.5065226554870605, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5403b539628d5cebbc2c89f287a9ed489bb0ba692e49c478701a8503aadd6709.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "5460ae1503409ba51cb192a74c58888da2aa619310ea2a7f65ba32a22065c107", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "da36aa5f39cb0fd21857611613169bea022d36b59dd826a8a3ae340101f37ffb", "generation_seconds_batch": 23.62247458798811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08638554811477661, "target_z": -0.20703124956981583, "ce": 6.086154937744141, "genuineness": 4.406930446624756, "identity": 0.768214225769043, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5460ae1503409ba51cb192a74c58888da2aa619310ea2a7f65ba32a22065c107.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "df9d3a08a7be2e6aafb6e81c3533122c8726e752dc8715c96553785a8468a3e8", "generation_seconds_batch": 16.64575722301379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03835216164588928, "target_z": -0.4375000068829468, "ce": 6.316492557525635, "genuineness": 4.055472373962402, "identity": 0.6462709903717041, "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_Infatuation/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "546ddabc112b88d644070215a0d8210261f8207ec398a55a2d8a4af00491858d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8912fccf20c37a232bd36aaba586d5b979ea7c1280cd14b2a67e216efbe4257c", "generation_seconds_batch": 25.04692650400102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08744264394044876, "target_z": -0.2050781308074864, "ce": 6.09409761428833, "genuineness": 4.193545341491699, "identity": 0.3880627751350403, "hypothesis": "The door is still open. I qu put your coat 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_Infatuation/546ddabc112b88d644070215a0d8210261f8207ec398a55a2d8a4af00491858d.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "5515ff35c6a922d5717270d8bf22b94edd4ad53ba375b838bdcd15f47fcc4551", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "20cfdcf7f41dec80cf1f5fdcf553294691cfb0549945bd73bae52f1c5e122a29", "generation_seconds_batch": 26.341403366997838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05044417083263397, "target_z": -0.2734375077433152, "ce": 6.213237762451172, "genuineness": 4.381826400756836, "identity": 0.639610230922699, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5515ff35c6a922d5717270d8bf22b94edd4ad53ba375b838bdcd15f47fcc4551.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "55aeb0eca4243ad7dca9badc59adf1067e142dca6535595dd3207706b36e9d7a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d0e126d646a751d37f26b1569f354661a38efecc82772e2360d662a8dac06ceb", "generation_seconds_batch": 23.798470308072865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0948423445224762, "target_z": -0.1914062444076057, "ce": 6.1894097328186035, "genuineness": 3.8797430992126465, "identity": 0.35594090819358826, "hypothesis": "The 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_Infatuation/55aeb0eca4243ad7dca9badc59adf1067e142dca6535595dd3207706b36e9d7a.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": "5615d4bc4ca525107f649d1aaab205e83459e2deb9d486f6572e970fd387a985", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d504a3f2b50238c364e1b8a78ceea221f57b2225a4f9bcb1d9731af2bde4ecfb", "generation_seconds_batch": 17.179115866078064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07581455260515213, "target_z": -0.2265625060225785, "ce": 6.046441555023193, "genuineness": 4.632867813110352, "identity": 0.6632760763168335, "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_Infatuation/5615d4bc4ca525107f649d1aaab205e83459e2deb9d486f6572e970fd387a985.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "5649436406e83c7265a82e8e84102d41535a1c429b511473418d226480dcbd9e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1d68ffc780000e5a289f86b2e36c161326ff96e209e8cc7a7dd8e7ff915e571c", "generation_seconds_batch": 17.383835167973302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2438933253288269, "target_z": 0.08398436833214525, "ce": 5.645336627960205, "genuineness": 3.7667744159698486, "identity": 0.3613462448120117, "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_Infatuation/5649436406e83c7265a82e8e84102d41535a1c429b511473418d226480dcbd9e.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "56973dc66e1a5a417b35d82f323c7f60db63ef1ffa0b924d76e948a6976261bd", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "28850bca413b232c2aafa423601be5d8ee52d38ecc16b5a33d0c2371fa8546b2", "generation_seconds_batch": 17.475542593980208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3686310350894928, "target_z": 0.3144531256452763, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.6164204478263855, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/56973dc66e1a5a417b35d82f323c7f60db63ef1ffa0b924d76e948a6976261bd.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "573df9f70c0b2c30651fc0863d5aa918df802c9fd1370dba06c866e91af92f15", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ddf96e2835726eece8c72bad2cfd2e8d481f0e5f98700b2c1d5089a40867dac6", "generation_seconds_batch": 17.307141129975207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2951626479625702, "target_z": 0.1787109518036239, "ce": 6.3641486167907715, "genuineness": 4.607763767242432, "identity": 0.38309699296951294, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/573df9f70c0b2c30651fc0863d5aa918df802c9fd1370dba06c866e91af92f15.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "5769c2200f7a198e550f399a277b33a7f2d64e09ef4bf791a3366f17e1c2570e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8506719f3ac67856a80d8c5d0bde374af2380cbd137cca7286c300dc58396171", "generation_seconds_batch": 26.041155007085763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12285546958446503, "target_z": -0.13964843889809858, "ce": 6.229123115539551, "genuineness": 4.494794845581055, "identity": 0.33457523584365845, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5769c2200f7a198e550f399a277b33a7f2d64e09ef4bf791a3366f17e1c2570e.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "578585f39a78bb5a589882a51060063724bb25deaafea2ea8cfc41c41efecd9c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6f15b1dd88fa0ab318ef63729f629e14e9f0d6e168d780ab34d8a3188b353c50", "generation_seconds_batch": 26.02610400202684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009810477495193481, "target_z": -0.3847656213434345, "ce": 6.1020402908325195, "genuineness": 4.482243061065674, "identity": 0.5562218427658081, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/578585f39a78bb5a589882a51060063724bb25deaafea2ea8cfc41c41efecd9c.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "57a5e6d86cce0eb591a1bc7d4f58f794a82c135ac3c8bd2d09687f7e02f60afb", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "594da77b4e1152531ad4fa664f186f28a723436ecbafda7f98412b9c4ce2e2d2", "generation_seconds_batch": 17.868831633008085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022959589958190918, "target_z": -0.32421876075460443, "ce": 6.046441555023193, "genuineness": 4.545003414154053, "identity": 0.7233932614326477, "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_Infatuation/57a5e6d86cce0eb591a1bc7d4f58f794a82c135ac3c8bd2d09687f7e02f60afb.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "57c4c16022100298e31364224a81f9b5e771999ac944d73f764f0866ba6be7ce", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "67c3500c338e22789e7bd21530b10bd19cf1732c03768be55cdd7d41da520758", "generation_seconds_batch": 17.372907920042053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 6.300607204437256, "genuineness": 4.607763767242432, "identity": 0.5984609127044678, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/57c4c16022100298e31364224a81f9b5e771999ac944d73f764f0866ba6be7ce.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "580312e592fd377bacae398040ebc1b59dcc1325949bf2cf8f7edc569bf20017", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e8ec41af9945663724d3c3324f096049f98cda9aa608c04390b42c5df037b6eb", "generation_seconds_batch": 27.04373802198097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10435623675584793, "target_z": -0.17382812048306615, "ce": 5.6334228515625, "genuineness": 3.7918784618377686, "identity": 0.5227850675582886, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/580312e592fd377bacae398040ebc1b59dcc1325949bf2cf8f7edc569bf20017.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "583d87614e81f832fd1150026a587b8034e5e5feb939c02bd1b6ecfc82039fbc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2e00381259ce0029c6c900667df96432c058f92465340c29c831efff08a10400", "generation_seconds_batch": 27.48518401395995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1461116522550583, "target_z": -0.0966796884679144, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.6584867238998413, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/583d87614e81f832fd1150026a587b8034e5e5feb939c02bd1b6ecfc82039fbc.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "5909c1fb59662253c22d01e2d7473e4325e36a808c7d09fda26332ac9f41b57c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7256e1af20d7416c68d371e14f69bcca218a71ae1aed6cf8c032142860833290", "generation_seconds_batch": 29.306264235987328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3929443359375, "target_z": 0.35937503613547095, "ce": 5.514282703399658, "genuineness": 4.457139015197754, "identity": 0.7762485146522522, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5909c1fb59662253c22d01e2d7473e4325e36a808c7d09fda26332ac9f41b57c.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "595cbcb0403e94bdbe08ce6f9366fed9e246c49984171e129175ad6ff49669ac", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e4ff3cacd1c3240aed425bedd3962d55d514fa43496059767e67466e88d79b51", "generation_seconds_batch": 17.789703018032014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3665168285369873, "target_z": 0.31054686058883, "ce": 5.708878040313721, "genuineness": 4.356721878051758, "identity": 0.5082083344459534, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/595cbcb0403e94bdbe08ce6f9366fed9e246c49984171e129175ad6ff49669ac.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "5a793642d0b3884b4df813255ad81958a5e0914b11807b5d334907eb8fae867f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6b8a7219342c26049d87a4bc6d5365a83f92c990dd407c266eaf8ad7a259fe25", "generation_seconds_batch": 22.83906665293034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 6.221180438995361, "genuineness": 4.406930446624756, "identity": 0.6872059106826782, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5a793642d0b3884b4df813255ad81958a5e0914b11807b5d334907eb8fae867f.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "5a864d0db6df84076bd0d737922354863531154883f64bd2df0815208a6d631b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "24438ac1c1467e5a8f3da160a7027f85e6d19ceb81c21bfaf7d1e19b6779e885", "generation_seconds_batch": 22.788213610067032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2563142478466034, "target_z": 0.1069335998263515, "ce": 6.022613525390625, "genuineness": 4.005263805389404, "identity": 0.45684748888015747, "hypothesis": "The 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_Infatuation/5a864d0db6df84076bd0d737922354863531154883f64bd2df0815208a6d631b.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "5add1193ac32f2dc3c800b40de27407362ab1edc18c52bcd90b7621ed949b28a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7dff630b658e9c081ba3813e0d85c78b01fd0278bbf5f01f59ca3ebce2a61469", "generation_seconds_batch": 23.340271739056334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6487623453140259, "target_z": 0.8320312908674968, "ce": 5.839932441711426, "genuineness": 4.444586753845215, "identity": 0.33250951766967773, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5add1193ac32f2dc3c800b40de27407362ab1edc18c52bcd90b7621ed949b28a.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": "5af1c3eb7447bb237aacd7502e5ae121b129eac8a8de66f09790092b763d94aa", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "01a40d3454462dbeb4c9f627c31ff0615f984a7ccea1f7da8690803ec076fd0c", "generation_seconds_batch": 23.739534029969946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.024609863758087158, "target_z": -0.4121093666114085, "ce": 5.681078910827637, "genuineness": 3.5973212718963623, "identity": 0.19006268680095673, "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_Infatuation/5af1c3eb7447bb237aacd7502e5ae121b129eac8a8de66f09790092b763d94aa.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "5b14bc1e2ee6c4e89ad023dd751ad35ff8ad50b946da734d4295ab1336833d84", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e00f2295343042bd651bf7de434c83905c20a28dd496a26194bcd7c378d656e2", "generation_seconds_batch": 23.46867728396319, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07370036095380783, "target_z": -0.23046874354723734, "ce": 5.522225379943848, "genuineness": 4.093128204345703, "identity": 0.5717440247535706, "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_Infatuation/5b14bc1e2ee6c4e89ad023dd751ad35ff8ad50b946da734d4295ab1336833d84.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": "5b77f5d76746dbc6d61c6128df27f7dac927df66a257c59c84f76cd9847fcc9a", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bad4aad5bc72e236a33f80ac4fcd9032eb45797c4f4e2c9c2e9b1c226131bff", "generation_seconds_batch": 17.188717864919454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22195851802825928, "target_z": 0.04345702667929311, "ce": 6.062326908111572, "genuineness": 4.570107460021973, "identity": 0.5389159917831421, "hypothesis": "Escribí el número en el sobre, léelelo 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_Infatuation/5b77f5d76746dbc6d61c6128df27f7dac927df66a257c59c84f76cd9847fcc9a.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "5bd2d83b5ff989e0a166af8b6416df0990a5cd9495135104b7d4dc80749e8c0b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b0d12d378e6ff0eab062f2e78b9bdee1b66cddfeff0209a9b2e9f72626cf882a", "generation_seconds_batch": 23.62247458798811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05678677558898926, "target_z": -0.2617187401057639, "ce": 6.0305562019348145, "genuineness": 4.632867813110352, "identity": 0.7538671493530273, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5bd2d83b5ff989e0a166af8b6416df0990a5cd9495135104b7d4dc80749e8c0b.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "5c05b4ce0971dbbeb81c3d40c429895c71cf8b821d68d2912e07b7bcf2db6c14", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0bff7b96be773e00a304312939e2afd1a5bbc98fcead694c3df0f21a4e08d3f6", "generation_seconds_batch": 26.238299524993636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9637778997421265, "target_z": 1.414062526671419, "ce": 5.462655067443848, "genuineness": 4.545003414154053, "identity": 0.7018869519233704, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Déis-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_Infatuation/5c05b4ce0971dbbeb81c3d40c429895c71cf8b821d68d2912e07b7bcf2db6c14.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "5d2e192d0c8f07dfa05cf7c28ca8d0d0c0f558385ab75c738b6810a7c6169eea", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d6288e7a5cd6b1740ae9a3f4970c96e55fe56acaeae1df186a8b56bd1423c55d", "generation_seconds_batch": 23.182461167918518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198737442493439, "target_z": -0.2890625129055253, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.48396921157836914, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5d2e192d0c8f07dfa05cf7c28ca8d0d0c0f558385ab75c738b6810a7c6169eea.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "5d75daea2f59823d4480ab4e62695693220fdff72f8a52a748d6ca4ccd199ca7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8a8ec9883010844ffa241b1f265fc5987db6c67d2d89521d8783095cc1e713da", "generation_seconds_batch": 24.03543922409881, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 6.252951145172119, "genuineness": 4.168440818786621, "identity": 0.2862147092819214, "hypothesis": "The 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_Infatuation/5d75daea2f59823d4480ab4e62695693220fdff72f8a52a748d6ca4ccd199ca7.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "5da8b354a7e3c20b65edbfdbfc8c097ed939a9433c3e4ced59c4d72def4a0255", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d76c83c00eef2b69a5d97d7d556d48c02b546bf7069735f1d93c96a52132eabe", "generation_seconds_batch": 18.21480709698517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18218515813350677, "target_z": -0.030029305935754244, "ce": 5.061550617218018, "genuineness": 4.356721878051758, "identity": 0.6936424374580383, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5da8b354a7e3c20b65edbfdbfc8c097ed939a9433c3e4ced59c4d72def4a0255.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "5db22927e324c9166c8f4448998274a42f003c158bc0e4118d142c5fc92134d2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5adb1aba068a19dfbf35fef2d2c5932b2209aa6f51bf236bafc525557e0c8e21", "generation_seconds_batch": 24.00509573495947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23437944054603577, "target_z": 0.06640625817349938, "ce": 5.752562999725342, "genuineness": 4.331617832183838, "identity": 0.573236346244812, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5db22927e324c9166c8f4448998274a42f003c158bc0e4118d142c5fc92134d2.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "5dff30e7f1168203290ebee72348f08834f94cd0c16ac36a6f9addb5c0e53f19", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "41e367dcea19687e159bd4fe7f56400f6b65799861934f1a4f95976be267476b", "generation_seconds_batch": 26.122552737942897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08797119557857513, "target_z": -0.20410156454337483, "ce": 6.046441555023193, "genuineness": 4.093128204345703, "identity": 0.2981864809989929, "hypothesis": "The 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_Infatuation/5dff30e7f1168203290ebee72348f08834f94cd0c16ac36a6f9addb5c0e53f19.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "51bdfe8a5e6311341bd4eb6a8483a3391739fa5a0d5a239a45baceffb9cdef3f", "generation_seconds_batch": 16.77719493804034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.062326908111572, "genuineness": 4.319066047668457, "identity": 0.7537428140640259, "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_Infatuation/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "5e3a20e79ad7303cdbabbea2a8d5804902529b4a37a2c15e5c39657302e6a658", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b253d3e9dca6d3b1a78a7376e1dbfb5f2794887642efeda6cb6f26a1e7b98cf4", "generation_seconds_batch": 25.928880390012637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02249567210674286, "target_z": -0.40820312908674966, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.6476161479949951, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5e3a20e79ad7303cdbabbea2a8d5804902529b4a37a2c15e5c39657302e6a658.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": "5ef9616167d4c5e23bdc82ddec4180b06cdd39f09ce489fe0f19c09f98620f8f", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79913a1858c2a88a57607c161e7e805f63a24545eb4f08cce27ea4e0719daacc", "generation_seconds_batch": 25.411017408012412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18277978897094727, "target_z": -0.028930649960524923, "ce": 5.903473377227783, "genuineness": 4.545003414154053, "identity": 0.5002869367599487, "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_Infatuation/5ef9616167d4c5e23bdc82ddec4180b06cdd39f09ce489fe0f19c09f98620f8f.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "5f310a6a700ea03d3d95f71a25538263257e845b78d5494e2f6f539f8a19aaaf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8a843ac1868f4fb378ba7c997888ec35147fe19a60894aac0aa44ff502642b7f", "generation_seconds_batch": 24.05426055600401, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3728594183921814, "target_z": 0.322265600694594, "ce": 5.609594821929932, "genuineness": 4.6203155517578125, "identity": 0.7243359088897705, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/5f310a6a700ea03d3d95f71a25538263257e845b78d5494e2f6f539f8a19aaaf.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "6005e52d726c72ca49996d4cb8ac39a235c8651cad89698abc2bb6af0fdcf9e7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9ed83f58299c0870bda51ccc777cc3171f34aa9d403494d708eae22ebbef2de9", "generation_seconds_batch": 23.1568539889995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1291980743408203, "target_z": -0.1279296712605473, "ce": 5.704906940460205, "genuineness": 4.758388519287109, "identity": 0.8284134864807129, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6005e52d726c72ca49996d4cb8ac39a235c8651cad89698abc2bb6af0fdcf9e7.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "60092ad17e2ad7aec7c85b3911d40a4dd64f7c54dc56c16292e6ceb4e8688d7d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8a1fda2df756911617a7e100725ed09799f812e20e1b56d99eadb85a8ca64925", "generation_seconds_batch": 18.304584442987107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12391257286071777, "target_z": -0.13769530636987548, "ce": 6.062326908111572, "genuineness": 4.6705241203308105, "identity": 0.5969578623771667, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/60092ad17e2ad7aec7c85b3911d40a4dd64f7c54dc56c16292e6ceb4e8688d7d.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "60101d892e0be309f0a69871ae943d7fc0ffcc2b63a09ef5c23bd5e0068ec90a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6ae9710b5b2007f4759ee93315aaa3f0d6c8a9bac8b97276e94b80cc9d9662d9", "generation_seconds_batch": 26.16281892999541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26133546233177185, "target_z": 0.11621093115478338, "ce": 5.720792293548584, "genuineness": 4.6956281661987305, "identity": 0.6429750919342041, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/60101d892e0be309f0a69871ae943d7fc0ffcc2b63a09ef5c23bd5e0068ec90a.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "603e168540aebcca2a6195af5db388e7627e1fc5ce4a4e4d108166cf96d214ba", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "193a343724dd9ed136deb370fd5bcdd6378f2e23020b3a719b8e08851409aad4", "generation_seconds_batch": 22.93575245095417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621577262878418, "target_z": -0.28125001032442026, "ce": 6.1020402908325195, "genuineness": 4.457139015197754, "identity": 0.524284839630127, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/603e168540aebcca2a6195af5db388e7627e1fc5ce4a4e4d108166cf96d214ba.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "609a090cb0efe870651e8aa6444002adbeea0fc90a4e3c539afe6862b2757353", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a70e51aa062694ed0c8d88c9e816107f7f5fa7a038704e36ea06ecfd56adc50e", "generation_seconds_batch": 22.94100840506144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007696285843849182, "target_z": -0.38085938381877565, "ce": 6.23706579208374, "genuineness": 4.507347106933594, "identity": 0.7070429921150208, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/609a090cb0efe870651e8aa6444002adbeea0fc90a4e3c539afe6862b2757353.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "613e90568c898b5719860eb05a77573f820a78788e0e1da3ab7c191cd969c0a6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e3597fa50987ce393e7c85b9d9db42549aee900c460ae57ad74bec2e5d76212f", "generation_seconds_batch": 17.36083770892583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198737442493439, "target_z": -0.2890625129055253, "ce": 5.418970584869385, "genuineness": 4.18726921081543, "identity": 0.40582484006881714, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/613e90568c898b5719860eb05a77573f820a78788e0e1da3ab7c191cd969c0a6.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "61d7875cc14f8e1a14426b7cb87457a0c8a782d9cbc86d3503a4e4c7ff9d87a8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e832d8a5ff3aeb15f6a2770936bddebcf29909947796da094e155201bf9ab3d5", "generation_seconds_batch": 19.092525899992324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012981772422790527, "target_z": -0.39062499139631646, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.44553667306900024, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/61d7875cc14f8e1a14426b7cb87457a0c8a782d9cbc86d3503a4e4c7ff9d87a8.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": "621901413272a167b9c000c9ddd3995e9647034aba84cf0b25b4c3e615c134a6", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb64085a2a022caac1a2e158674dcbbc1a351b4aab7a68e60764e69a7fd312f2", "generation_seconds_batch": 16.647802694002166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12444111704826355, "target_z": -0.1367187538716576, "ce": 5.152891159057617, "genuineness": 4.344170093536377, "identity": 0.5013568997383118, "hypothesis": "Las llaves están en la mesa de la cocina, miren el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/621901413272a167b9c000c9ddd3995e9647034aba84cf0b25b4c3e615c134a6.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "6271dc722e4c9cfddb5510eabf71efdb37e92d85af8d2a4f265464328ba698b6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0056a3a36c6f91bde3e9d0abb9eb24f741c82faf2f507b9c77aca21a9a009bf3", "generation_seconds_batch": 19.95846700889524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0906139463186264, "target_z": -0.19921874698871075, "ce": 6.046441555023193, "genuineness": 4.720732688903809, "identity": 0.7630048394203186, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6271dc722e4c9cfddb5510eabf71efdb37e92d85af8d2a4f265464328ba698b6.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "627a6e3a627e180cdf1314a0e4bf93d9a2afaf78b39233e0d75319a159f1d6d2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce52d555a23d4d87045f691a88d52a4fa37d1619eee34b5f5669a8df7f5615d8", "generation_seconds_batch": 32.48294028406963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5007684230804443, "target_z": 0.5585937280606069, "ce": 5.7406487464904785, "genuineness": 4.218649387359619, "identity": 0.5355168581008911, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/627a6e3a627e180cdf1314a0e4bf93d9a2afaf78b39233e0d75319a159f1d6d2.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "62f60980c0ba4a7caa2e8d2561a72e1401b3f5a15ac381833bbbd7188a692de3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5c92e5c3e6aa65f91f03ca76a14d4ab067cd5acea169221fb50cf7682b966e7d", "generation_seconds_batch": 25.326649537077174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18416722118854523, "target_z": -0.026367192769756177, "ce": 6.403861999511719, "genuineness": 4.557555198669434, "identity": 0.26149260997772217, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/62f60980c0ba4a7caa2e8d2561a72e1401b3f5a15ac381833bbbd7188a692de3.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "62fec5911991a66eb6fb8afefd910a266004c2798c0fe9a2cd8c246022d22b9e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e1d60c6001825d8d7f1d922e1c5b0011a1ff51c619bf57b4190675a85ffc59e0", "generation_seconds_batch": 17.310886939056218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6212777495384216, "target_z": 0.7812500103244203, "ce": 5.613565921783447, "genuineness": 4.093128204345703, "identity": 0.31957605481147766, "hypothesis": "The 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_Infatuation/62fec5911991a66eb6fb8afefd910a266004c2798c0fe9a2cd8c246022d22b9e.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "63c9b7ff349d725841bff65f29704f689c661c00c17c46babc43fe0f69acf3a9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c4d23fbf5dadb53968362d7963860980520aad1169b31519b04c9039f9f2c948", "generation_seconds_batch": 25.12970911199227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002874717116355896, "target_z": -0.3613281136001193, "ce": 6.38003396987915, "genuineness": 4.243753433227539, "identity": 0.3873465061187744, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/63c9b7ff349d725841bff65f29704f689c661c00c17c46babc43fe0f69acf3a9.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": "63df2f4f9b5bf8d57a634405dad35677c2df6dbf47e9bbb9d8c2542f6d0253d2", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ddd70db48af7f7b3f24971d960b21a142b0bbfae8b07e3c7d22221b7d757083f", "generation_seconds_batch": 18.118072243989445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 5.959072113037109, "genuineness": 4.65797233581543, "identity": 0.7406798601150513, "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_Infatuation/63df2f4f9b5bf8d57a634405dad35677c2df6dbf47e9bbb9d8c2542f6d0253d2.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "63eb28622904e80403488b0672a7ddb550c8d4b3499ce1ae9e753315a97b34a9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0aeb899c9c08d358e0816cf99a92392250f83d2d88523f9e4447408d46f89163", "generation_seconds_batch": 23.625405644997954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07052905857563019, "target_z": -0.23632812736601297, "ce": 5.990842819213867, "genuineness": 4.394378662109375, "identity": 0.32678210735321045, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/63eb28622904e80403488b0672a7ddb550c8d4b3499ce1ae9e753315a97b34a9.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": "64323a3fed8e90ce8f76a041852792b80a253f5a0a5c379f3ab7adf080da1fe8", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "141145e1cbfd606bf92161ca632d951db1b71514ccf3fbdb7a64892505a1a7d6", "generation_seconds_batch": 25.592071415041573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.047272875905036926, "target_z": -0.27929687779619716, "ce": 5.831989288330078, "genuineness": 4.519899368286133, "identity": 0.4881247878074646, "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_Infatuation/64323a3fed8e90ce8f76a041852792b80a253f5a0a5c379f3ab7adf080da1fe8.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "64aea1a2162c37ea29425c4946c1c6be820c3c3e2c5b922a612ce92ab2de3b1a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41f3e41b9feba112e17b26cf1773ed021550b75e08013bf5e333b0b8831c1968", "generation_seconds_batch": 26.073071796097793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41302919387817383, "target_z": 0.3964843614491984, "ce": 5.959072113037109, "genuineness": 4.356721878051758, "identity": 0.3195294737815857, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/64aea1a2162c37ea29425c4946c1c6be820c3c3e2c5b922a612ce92ab2de3b1a.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": "64b24bc416e53cadf5766883051104389711b76d8d3821b9fd459ecc65f66764", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ae0b42fb32b4e6cd89b7f86f77a233ba431ba8a940eb02c8de1854baf127703", "generation_seconds_batch": 17.643648650031537, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0483458042144775, "target_z": 1.570312468166371, "ce": 5.71682071685791, "genuineness": 4.356721878051758, "identity": 0.4484748840332031, "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_Infatuation/64b24bc416e53cadf5766883051104389711b76d8d3821b9fd459ecc65f66764.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "65974fdb56662047add911117048f5b2df60e7b625ce50121f90d4bc6864095e", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "17c2d93e7d493c697225363c9725d0a8041f8c22dc00a82f2dba64c1933676c7", "generation_seconds_batch": 17.320329534006305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04832997918128967, "target_z": -0.27734374526797406, "ce": 6.157639026641846, "genuineness": 4.6956281661987305, "identity": 0.6941885948181152, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/65974fdb56662047add911117048f5b2df60e7b625ce50121f90d4bc6864095e.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "663521451db7bc41722a555ed349ea4eb1f63a35f43d42d6715a9eba2097528f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "42b8d508947f632d393427c43139d564537ab449904537e067d33c68cb8bc2ae", "generation_seconds_batch": 24.090061611961573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3379751443862915, "target_z": 0.2578124750493177, "ce": 5.748591423034668, "genuineness": 3.8797430992126465, "identity": 0.41943517327308655, "hypothesis": "The 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_Infatuation/663521451db7bc41722a555ed349ea4eb1f63a35f43d42d6715a9eba2097528f.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": "66388feaed65dd99a382efa78866d94dabe543c56d1ba7d848bb29fb00a25a9e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9fd2fb50ac861adcb954b2bf3c4096462c9a4367c771bea5a0eb570e249360c", "generation_seconds_batch": 17.458740954985842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 6.062326908111572, "genuineness": 4.6705241203308105, "identity": 0.49392420053482056, "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_Infatuation/66388feaed65dd99a382efa78866d94dabe543c56d1ba7d848bb29fb00a25a9e.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "66deefaaf37e5ffde5d850b84213bc3cdf4b4adbb744642a0181088e45cbc76e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0f05fc1b513aa5bec1fe9a40794e261a4fde0107d2b139cd88ffe45ecb987303", "generation_seconds_batch": 23.384977680980228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6910462975502014, "target_z": 0.9101562616149728, "ce": 5.689021587371826, "genuineness": 4.124508857727051, "identity": 0.4192061126232147, "hypothesis": "The 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_Infatuation/66deefaaf37e5ffde5d850b84213bc3cdf4b4adbb744642a0181088e45cbc76e.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "66f622b722d72f3d8832de1d0241de8931cc0bf8b5f3757fab90eb27e09448e8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bcae242ede8e295eada75ddd7984dacbec6ba5e719316a9ce7b4b9767314e2cb", "generation_seconds_batch": 24.116994161973707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22248706221580505, "target_z": 0.04443357917751098, "ce": 5.796247482299805, "genuineness": 4.432034492492676, "identity": 0.6174037456512451, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/66f622b722d72f3d8832de1d0241de8931cc0bf8b5f3757fab90eb27e09448e8.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "670244bd65a8c46e440326ab5d647731c8f503b2ac1cddc2e825943c585b1d87", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0611e6b6f827a5b323938f1389a693888aa9bb1262773103bbfd86b570af4751", "generation_seconds_batch": 18.229127648985013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14505454897880554, "target_z": -0.09863282099613752, "ce": 5.839932441711426, "genuineness": 3.9801597595214844, "identity": 0.414795458316803, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/670244bd65a8c46e440326ab5d647731c8f503b2ac1cddc2e825943c585b1d87.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "6721bf8f6c43f7d1af0eea280774e2f2a9d4729c987d4d231e245d486a77d1a3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6f17c972bf07a6006e6ee8dc6495ccb4da391253a30e72e844ed175b8140dd4", "generation_seconds_batch": 24.097254652064294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.027781158685684204, "target_z": -0.41796873666429046, "ce": 5.863759994506836, "genuineness": 4.532451152801514, "identity": 0.7004045248031616, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6721bf8f6c43f7d1af0eea280774e2f2a9d4729c987d4d231e245d486a77d1a3.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": "6726c99651b7632d4fdd4d8fb3b7f4efb0cef8f823f5e211d46497ae73a3e970", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "ff47030af97ae200e6b6d3890a1bd9a2a8507ea3838d72372ff4ff40edab1519", "generation_seconds_batch": 22.85165358602535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030359283089637756, "target_z": -0.3105468881206174, "ce": 6.205295085906982, "genuineness": 4.519899368286133, "identity": 0.6241077184677124, "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_Infatuation/6726c99651b7632d4fdd4d8fb3b7f4efb0cef8f823f5e211d46497ae73a3e970.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "6737db8bc42a91473bbdbc2af1027f0e6c2a03e2a9900a627b7a9e96466249e9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f3c9944ef5e959e6429eee2667d07e9ac2a6291fbca1ec3eba23f8b46c1d4872", "generation_seconds_batch": 23.055694174952805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10171348601579666, "target_z": -0.17871093803773022, "ce": 5.40705680847168, "genuineness": 4.607763767242432, "identity": 0.3467714190483093, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6737db8bc42a91473bbdbc2af1027f0e6c2a03e2a9900a627b7a9e96466249e9.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "6750273a5f33be97b63ceee66ee88d50bd402ee0f66e7b49cfad9f804f23ec00", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f813dc83273993ff346813b1a615be67f23dc5e3289635f2ef4ba5372f985a78", "generation_seconds_batch": 19.36441585503053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26926371455192566, "target_z": 0.13085938381877565, "ce": 6.09409761428833, "genuineness": 4.011539936065674, "identity": 0.23903222382068634, "hypothesis": "The 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_Infatuation/6750273a5f33be97b63ceee66ee88d50bd402ee0f66e7b49cfad9f804f23ec00.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "677971d24b2852ba636c4c41c3d0c8a1b314c6fe49186889978dac05f5902e1d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bb7d43e0d169a459cd4135de001a42cafa30d6c46de99dc8a42e97255b4e3497", "generation_seconds_batch": 23.240895787021145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08479990065097809, "target_z": -0.2099609345962568, "ce": 6.260893821716309, "genuineness": 4.68307638168335, "identity": 0.75275719165802, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/677971d24b2852ba636c4c41c3d0c8a1b314c6fe49186889978dac05f5902e1d.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "6781b59306c9ea77d17f8196863284f25aef595dffd5a1554c6e6f206678ee34", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "63565a9444894fe039675ca859b06ed2782bc832494f059d0ffca17c8ce00a5e", "generation_seconds_batch": 23.830663322936743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12179837375879288, "target_z": -0.141601557660428, "ce": 6.125868320465088, "genuineness": 4.6956281661987305, "identity": 0.8364617228507996, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6781b59306c9ea77d17f8196863284f25aef595dffd5a1554c6e6f206678ee34.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "67890058cbfc252488f760d87eaacd5d380e9a50babbf6fdf6fa86f53026746e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3bc5c5a600d17dffe53109ed7bbab3970d25c6ed5333fc1d7493aa730d32af6d", "generation_seconds_batch": 17.730980328982696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05678677558898926, "target_z": -0.2617187401057639, "ce": 5.677107334136963, "genuineness": 4.168440818786621, "identity": 0.4754827916622162, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/67890058cbfc252488f760d87eaacd5d380e9a50babbf6fdf6fa86f53026746e.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "67f0d65387fc749845620c0e8b0e9e8a57436280b76009cb1e16cd442b19e42b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0821ba6e58f9a30a43e14f39a606a5176ef8f433399edf1861e76972923a516c", "generation_seconds_batch": 27.372013543033972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017674103379249573, "target_z": -0.33398436833214523, "ce": 6.324435234069824, "genuineness": 4.720732688903809, "identity": 0.5464915633201599, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/67f0d65387fc749845620c0e8b0e9e8a57436280b76009cb1e16cd442b19e42b.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": "680325353396093fe9ca37e5f2141a4495f7bf6698c6ee6afa180e1efb3f61ad", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "a2f5474058948cd5715af432e0d18fe5e50076855c776bb007ea614078a84802", "generation_seconds_batch": 18.118072243989445, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09959928691387177, "target_z": -0.18261718932828275, "ce": 5.95112943649292, "genuineness": 4.607763767242432, "identity": 0.8440707921981812, "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_Infatuation/680325353396093fe9ca37e5f2141a4495f7bf6698c6ee6afa180e1efb3f61ad.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "682f63a8085482bef2127f60491c5601421313d20392aef255d0119a090bc1cc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19593fdd4b13c9f4199692559a7c1b3c8febdfad6541eb338fabfaaeaf52385a", "generation_seconds_batch": 24.03287954197731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002874717116355896, "target_z": -0.3613281136001193, "ce": 6.23706579208374, "genuineness": 4.7081804275512695, "identity": 0.5228250622749329, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/682f63a8085482bef2127f60491c5601421313d20392aef255d0119a090bc1cc.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "68515953d3a80cebd8a2243852953d4da2a7a22dbcdbc523568974cbe1aa9810", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "af99b2e2050b7dec8e73dd612cb9b3f647f838b2a34c8b971bd26cb5e6b20c49", "generation_seconds_batch": 19.722007630974986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32264721393585205, "target_z": 0.2294921772831258, "ce": 5.974957466125488, "genuineness": 4.243753433227539, "identity": 0.2794169783592224, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/68515953d3a80cebd8a2243852953d4da2a7a22dbcdbc523568974cbe1aa9810.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "6916d6f0af2399df0a668d07b5993a2fed7ba86dc8f0c89c14a6433ac200892c", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7d2c6751a2769a1ce0e62b7b0b2fb45e206b6f944cded5739ac275a213a70075", "generation_seconds_batch": 17.295656098984182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009217306971549988, "target_z": -0.3496093734943554, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.4834587574005127, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6916d6f0af2399df0a668d07b5993a2fed7ba86dc8f0c89c14a6433ac200892c.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "6928ec8b03c5a7fca2fbce9adac661da53173f359ddbcc3ea74203595e719014", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3bd5d475d871be36d75fc2b33cebb7289bf38b6d64a691ea3b592957a161b55d", "generation_seconds_batch": 24.099292289000005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12021271884441376, "target_z": -0.14453125645276266, "ce": 5.990842819213867, "genuineness": 4.632867813110352, "identity": 0.5529016852378845, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6928ec8b03c5a7fca2fbce9adac661da53173f359ddbcc3ea74203595e719014.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "69aa20e67b4cbe13b9b27d60202a6bfd3f5e0966ffb6ddb633f3bb302902bc15", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ad08b1fd7feb136ab82e462b66fb5706f0b20c7c3dc6be965072313f060ae686", "generation_seconds_batch": 23.502638636971824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01509597897529602, "target_z": -0.39453125645276266, "ce": 6.0146708488464355, "genuineness": 4.3504462242126465, "identity": 0.6654356122016907, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/69aa20e67b4cbe13b9b27d60202a6bfd3f5e0966ffb6ddb633f3bb302902bc15.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "69ad9ee26e6b983f50264c22bd07ace75e823129f19a7783b5cb6817cf7a7992", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "38897acfeb33148127a658294e04c9650a0070040cad71d94574f9f698315b62", "generation_seconds_batch": 23.733570913085714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0763431042432785, "target_z": -0.22558593975846694, "ce": 6.062326908111572, "genuineness": 4.419482707977295, "identity": 0.5888543725013733, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/69ad9ee26e6b983f50264c22bd07ace75e823129f19a7783b5cb6817cf7a7992.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "6a1affdc573ac9f2550782bd571375f93368c5fe4d2d075dd7d5bd52eda09cd3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "552b0e6e59e31a64aceac91ec8c1f7a7bb2b76334788efca67c61ace867c35af", "generation_seconds_batch": 17.868831633008085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03987318277359009, "target_z": -0.29296875043018417, "ce": 6.165581703186035, "genuineness": 4.356721878051758, "identity": 0.47949132323265076, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6a1affdc573ac9f2550782bd571375f93368c5fe4d2d075dd7d5bd52eda09cd3.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "6a237d01865638208c5e6ee7cf19cf295b8e6a64ede1425fcdd1a912a25b9a0d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9f8836f4938509a3d19911ee3d4b654648d32eb5844ca522b23c3ae3a56006f4", "generation_seconds_batch": 23.323735730024055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03458768129348755, "target_z": -0.3027343855395124, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.8602230548858643, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand t'es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6a237d01865638208c5e6ee7cf19cf295b8e6a64ede1425fcdd1a912a25b9a0d.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": "6a57fa235870c3cc5046d7cdd51dc1747518be6d70167ec852f306939b30878c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "20ac98669defb46b5c897b10269c60d08f49de6d6accdd9d100308e24948d5f0", "generation_seconds_batch": 18.85514882497955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024016693234443665, "target_z": -0.32226562822638133, "ce": 5.831989288330078, "genuineness": 4.005263805389404, "identity": 0.614297091960907, "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_Infatuation/6a57fa235870c3cc5046d7cdd51dc1747518be6d70167ec852f306939b30878c.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "03a9a98107db7df5acd4e6b3ab79ef55355118f99a3aa03f5e0a5bff0469c895", "generation_seconds_batch": 20.152974365046248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008753374218940735, "target_z": -0.3828124888152114, "ce": 6.403861999511719, "genuineness": 4.068024158477783, "identity": 0.3005371391773224, "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_Infatuation/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "6aa3ad5d171a54e7c8c8a046057c4518d07d605cf1e802186ebda522b2c55219", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a9c87cb8f41f0130f14d5ea33b205ec2203b39b331968ce23dfda8980e70570", "generation_seconds_batch": 23.350679737050086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10118493437767029, "target_z": -0.17968750430184177, "ce": 6.3641486167907715, "genuineness": 4.413206577301025, "identity": 0.38132280111312866, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6aa3ad5d171a54e7c8c8a046057c4518d07d605cf1e802186ebda522b2c55219.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "6af2e072c66f43a353135a05124b5a4873dc5b50cbb235fabd0673eb6c9d1f9e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "abd8f6d72416204f34b9f6147b9d5946f63e28bf7becf4233690a607df7b67af", "generation_seconds_batch": 22.948762655025348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.008160203695297241, "target_z": -0.3515625060225785, "ce": 4.870926380157471, "genuineness": 4.262581825256348, "identity": 0.10929519683122635, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6af2e072c66f43a353135a05124b5a4873dc5b50cbb235fabd0673eb6c9d1f9e.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "6af4b764970e375fb899241af334ce1ffc88673287de1db3b8cf031a51e065bc", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1011edee7b9e72d9fa3ddcde8498e7dfa59507f815d9812f2aa40f9ce9c31221", "generation_seconds_batch": 17.372042556060478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07211470603942871, "target_z": -0.233398442339572, "ce": 6.086154937744141, "genuineness": 4.507347106933594, "identity": 0.784076988697052, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6af4b764970e375fb899241af334ce1ffc88673287de1db3b8cf031a51e065bc.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "6b303b2a6920932df26b428719e6f06b0987a8020cf154b2e543d1a4feff6edd", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3a07efe0f394e0637bfd35300fc1c2d82cf2e44d85806e4d1a92ccc8bd33d467", "generation_seconds_batch": 17.633243234013207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09431379288434982, "target_z": -0.19238281067171725, "ce": 6.229123115539551, "genuineness": 3.9676074981689453, "identity": 0.22813105583190918, "hypothesis": "The 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_Infatuation/6b303b2a6920932df26b428719e6f06b0987a8020cf154b2e543d1a4feff6edd.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "6b3df90d304421a9fdd4deea29c89ff117ee50d110c06755d72fc71c2b4048b3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1bc2383acc2a42182432b2fb54ccf769491335cbb837448d25dcf12b5a03adbf", "generation_seconds_batch": 22.858118447940797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 6.284721851348877, "genuineness": 4.758388519287109, "identity": 0.6714009642601013, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6b3df90d304421a9fdd4deea29c89ff117ee50d110c06755d72fc71c2b4048b3.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "608dd60a530343097d5093abe8ca790dca92f58b72ff77e2e5ecb1e89e20619b", "generation_seconds_batch": 18.127504483098164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04515868425369263, "target_z": -0.283203115320856, "ce": 6.1020402908325195, "genuineness": 4.457139015197754, "identity": 0.6736350059509277, "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_Infatuation/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "6b98176389d672e4744a362eedc9a6f7d4af75ef8deb98ade6a8e1fa28048dc3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "36fad3091181041693fe707a0c6b3b09e48033ee1399af7c8bca600b71bfb2c7", "generation_seconds_batch": 24.54896349494811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16091103851795197, "target_z": -0.06933594319994035, "ce": 5.538110733032227, "genuineness": 4.432034492492676, "identity": 0.3879064619541168, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6b98176389d672e4744a362eedc9a6f7d4af75ef8deb98ade6a8e1fa28048dc3.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "6bfda5b757dbd314358e9a7088a15f2d62048bd61293cfa9773f3af4470979dd", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b63edb858fb11ad6caee6e5d344b108cae538ab14975630abfe7f86bc21108f9", "generation_seconds_batch": 17.49466701899655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0066391825675964355, "target_z": -0.37890625129055255, "ce": 5.974957466125488, "genuineness": 4.582659721374512, "identity": 0.6771649718284607, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6bfda5b757dbd314358e9a7088a15f2d62048bd61293cfa9773f3af4470979dd.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "6c1633edfc2b55b3dd16bd532575f5e81ea3a86f7d9b82d7b23df11839c436d3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5ab56651ff2d8cc436ffd94d1cd2c5f8d803e49b85a380703b25e01cec29e41e", "generation_seconds_batch": 25.452081073075533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16606439650058746, "target_z": -0.05981445998106033, "ce": 6.141753673553467, "genuineness": 4.7081804275512695, "identity": 0.6115602254867554, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6c1633edfc2b55b3dd16bd532575f5e81ea3a86f7d9b82d7b23df11839c436d3.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "6c608309cff1f4c8ecbad2d07dfc8fed7aed6475bba45399f3ac7bac9405af1a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fc19984190ff794fb274465a257c1a1f3bb50190f5ad91bb2cfbfb7ba7586797", "generation_seconds_batch": 23.982885726029053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.6506829261779785, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6c608309cff1f4c8ecbad2d07dfc8fed7aed6475bba45399f3ac7bac9405af1a.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "6c845f1ad7cb952cf345745b808e6d670ec4969061ab14c973decb715c17ba1b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2409d3b3c8783c8f4bc6d27e3fc51d72a8a985e8fdd802ed5ee23acff259e544", "generation_seconds_batch": 24.681338221998885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05044417083263397, "target_z": -0.2734375077433152, "ce": 6.348263263702393, "genuineness": 4.595211505889893, "identity": 0.5993877649307251, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6c845f1ad7cb952cf345745b808e6d670ec4969061ab14c973decb715c17ba1b.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": "6d15c4c72b3f49ff63a1c38a6aaf378f652c63b7e183355ac2e84816c8e95a3e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "05173af7fee530b3e5210c6d4b88971448b5924f31a99c670cc87510db6d3231", "generation_seconds_batch": 17.90445232798811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05572967231273651, "target_z": -0.263671872633987, "ce": 5.5738525390625, "genuineness": 4.344170093536377, "identity": 0.2255568504333496, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6d15c4c72b3f49ff63a1c38a6aaf378f652c63b7e183355ac2e84816c8e95a3e.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "6d2edb533e1301f36cf40735d821bcdf838be2b4a054452b03fcaba9debc9dc6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "197b4b544b78dc361e0f737649297612ca6f42efc3a435f79b186a991c44a0ef", "generation_seconds_batch": 24.287753941025585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13104799389839172, "target_z": -0.12451170998499737, "ce": 5.855817794799805, "genuineness": 4.6705241203308105, "identity": 0.47162359952926636, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6d2edb533e1301f36cf40735d821bcdf838be2b4a054452b03fcaba9debc9dc6.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "6d884274586d7c2de298dda40a5babc09fcb3eaeb78fb97d49f11e95b6b328b1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "39afbbbd46c52ed42af983f70200a78bc00ac1eefb2b6855145656c4e762d9a5", "generation_seconds_batch": 23.469351275009103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198737442493439, "target_z": -0.2890625129055253, "ce": 6.038498878479004, "genuineness": 4.093128204345703, "identity": 0.6078404784202576, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6d884274586d7c2de298dda40a5babc09fcb3eaeb78fb97d49f11e95b6b328b1.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "6d8fed390bba70450d6c237f05eaff3a2334f4a8b7e4a3440ae0ab27cecd6204", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cb926d975b4d995866fa9bf41e5f80d6304c18aa45d23db7aa9d07e4318d74c7", "generation_seconds_batch": 27.235756952897646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10277058184146881, "target_z": -0.1767578192754008, "ce": 6.157639026641846, "genuineness": 3.9048471450805664, "identity": 0.29538652300834656, "hypothesis": "The 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_Infatuation/6d8fed390bba70450d6c237f05eaff3a2334f4a8b7e4a3440ae0ab27cecd6204.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "6dd463d44316f5e0c374c3b13e1f496d22cf136cede5381df554c12e7a4bf699", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bac8011d7b22408f628fcdef8ff1f9067bc25b06b4a4fbf9e7f5b480e8c1275", "generation_seconds_batch": 18.094562384998426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5049968361854553, "target_z": 0.5664062581734993, "ce": 5.462655067443848, "genuineness": 4.394378662109375, "identity": 0.4348159432411194, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6dd463d44316f5e0c374c3b13e1f496d22cf136cede5381df554c12e7a4bf699.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": "6df179c2003119e1f64f259a8515113794bd7473ea6760bd739fe31c712fa739", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "443d27b5d1a9e2cbc267c1c00adf9bcefe7df1f3f8dec1aa7dfb96997333b001", "generation_seconds_batch": 24.648213448002934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006046012043952942, "target_z": -0.35546874354723734, "ce": 5.665193557739258, "genuineness": 4.469690799713135, "identity": 0.6351611614227295, "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_Infatuation/6df179c2003119e1f64f259a8515113794bd7473ea6760bd739fe31c712fa739.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "6df992541a0c43e9d13c7bc568760a3deb006f0b3e16a992c82f9fbe98537b5e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "29e16f86f40d951da278c6df2fa8162b171907e62101706b9c6c86ff40cd3ff2", "generation_seconds_batch": 23.160426275921054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2608069181442261, "target_z": 0.11523437865656551, "ce": 5.696964263916016, "genuineness": 4.7458367347717285, "identity": 0.5989372730255127, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6df992541a0c43e9d13c7bc568760a3deb006f0b3e16a992c82f9fbe98537b5e.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "6e74ef290b68036802c2f20be5ce2043961bdec5e692a85766b9c3eebc832048", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "38ac5e68d938f2572297b3313e1f8ce95190a3d43310f1d8d74a32a96f97eed5", "generation_seconds_batch": 23.212775830063038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03670188784599304, "target_z": -0.2988281204830661, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.6072869300842285, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6e74ef290b68036802c2f20be5ce2043961bdec5e692a85766b9c3eebc832048.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "6ee77245134de00a372e90a97c52114ddb9cb8d13ce67f94f6f6bf6d781d9851", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4900d3a5cf253f54d6fa1b116ed12451aa46834db1b2c37684763375a7ae3a0f", "generation_seconds_batch": 24.177380174049176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06682921946048737, "target_z": -0.2431640499171128, "ce": 5.855817794799805, "genuineness": 4.344170093536377, "identity": 0.5583465099334717, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6ee77245134de00a372e90a97c52114ddb9cb8d13ce67f94f6f6bf6d781d9851.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "6f49fd89a520fa5f9f0409a8706a813a7a056c27befe90af52893b29936cfb20", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "637b65debd2d41e3656dd0da5c60bb2468a3e0cf7379fc0494891713b7f90a27", "generation_seconds_batch": 24.977512422017753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01344570517539978, "target_z": -0.34179687091325034, "ce": 6.125868320465088, "genuineness": 4.494794845581055, "identity": 0.44061243534088135, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6f49fd89a520fa5f9f0409a8706a813a7a056c27befe90af52893b29936cfb20.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "6fdcc37866d957187d7fabbf09a244ce56a01014934c8f5839992f939bd73fd5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "88409a24c9dfff2bea3e67c3bcc7677e220b1c2581a7f482157606a9454d2519", "generation_seconds_batch": 23.22913279396016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1313122659921646, "target_z": -0.12402343373588845, "ce": 6.165581703186035, "genuineness": 4.7458367347717285, "identity": 0.799436092376709, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/6fdcc37866d957187d7fabbf09a244ce56a01014934c8f5839992f939bd73fd5.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "70f43d587bc7e117ac1fa8b8e8baf7efaa63ddc7dfc865568b1463af566ce9c0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e7446eae394624da7d0ca6732549be20ddf9da435b80e48dc5effce305cee21f", "generation_seconds_batch": 23.775733230053447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007696285843849182, "target_z": -0.38085938381877565, "ce": 6.022613525390625, "genuineness": 4.482243061065674, "identity": 0.5530291795730591, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/70f43d587bc7e117ac1fa8b8e8baf7efaa63ddc7dfc865568b1463af566ce9c0.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "7135380f50ab69de5282f469ef6e1e3e8cf5b2b2b5421372790a26ee6dacfdd6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bdffeb1d031d545c0d43c528314102083fe1e963d5ab1279e7d14e15bb7d4fa1", "generation_seconds_batch": 17.04781609692145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14056187868118286, "target_z": -0.1069335998263515, "ce": 5.673136234283447, "genuineness": 4.13078498840332, "identity": 0.4018937647342682, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7135380f50ab69de5282f469ef6e1e3e8cf5b2b2b5421372790a26ee6dacfdd6.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "718d892ed91c8f4a1eb999232bfdf58fda4b559d8a2e765390f2a52b8a5f05ba", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "61a24ed6ae3e273fad7c85a42a4f049bbb21f41bcaa44736e8d4a92369c8c91f", "generation_seconds_batch": 27.514330678037368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2107929140329361, "target_z": 0.022827155548982188, "ce": 5.279973983764648, "genuineness": 4.193545341491699, "identity": 0.45256561040878296, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/718d892ed91c8f4a1eb999232bfdf58fda4b559d8a2e765390f2a52b8a5f05ba.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "719eddf0d2ac0a8a34256ad536a499c3bf9e69855adca67cd7cf6879559ccfc3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24b9d2e577e848f7ffb6f121538816e6305c10a2aea616436272215060615703", "generation_seconds_batch": 17.04781609692145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10594188421964645, "target_z": -0.17089843545662517, "ce": 5.911416053771973, "genuineness": 4.381826400756836, "identity": 0.23763316869735718, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/719eddf0d2ac0a8a34256ad536a499c3bf9e69855adca67cd7cf6879559ccfc3.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": "72012c500130850978dd64424cf0aee742ca66c20761a74c443ee489e62f847d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "22a399fa8d4e468cafd68b5e7401103c5fcce30e601e5c01cc2b693c1faa118e", "generation_seconds_batch": 18.310121631016955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00029659271240234375, "target_z": -0.3671875111847886, "ce": 6.229123115539551, "genuineness": 4.457139015197754, "identity": 0.4302479922771454, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Wel me, wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/72012c500130850978dd64424cf0aee742ca66c20761a74c443ee489e62f847d.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "723a258717afed8de940df987b7fccc2d51c2bde56316c8db6254f1b2732abd7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "29dab82060847c056cab48446b806730693aa5ef4d39f786f3aa55e85d79d8f6", "generation_seconds_batch": 25.98978556098882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 6.141753673553467, "genuineness": 4.494794845581055, "identity": 0.5238968133926392, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/723a258717afed8de940df987b7fccc2d51c2bde56316c8db6254f1b2732abd7.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "7288003a6d7332f3fcf006568baad12d48ed4e33dea0409f911eab92aa790581", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bca147a642d371d34d17edc86c421a13a7c0f3aa79e3efc13518ec9e3425ac4b", "generation_seconds_batch": 24.174431374995038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03458768129348755, "target_z": -0.3027343855395124, "ce": 6.332377910614014, "genuineness": 4.344170093536377, "identity": 0.5390413999557495, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7288003a6d7332f3fcf006568baad12d48ed4e33dea0409f911eab92aa790581.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "72a386c4fe84efd52dd99102e1c26afc8b7c330dec111e15d4412789ca0e220b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e6f65ec5bbd7edd7f9986f33bab8ff817adc4225787d469ffe1487e8aa0d1029", "generation_seconds_batch": 23.948409872013144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 6.038498878479004, "genuineness": 4.632867813110352, "identity": 0.5308473110198975, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/72a386c4fe84efd52dd99102e1c26afc8b7c330dec111e15d4412789ca0e220b.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "72ce16302c8c1f3ac62bff7dc915e765096a1585331874a9c7a65d13b4b7ff58", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7818b0dc8e9588e43433ee455fcd857ee616dfb83f1bec5faf846b0429b70014", "generation_seconds_batch": 17.03581111400854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20061832666397095, "target_z": 0.004028313469882923, "ce": 5.855817794799805, "genuineness": 4.645420074462891, "identity": 0.47839656472206116, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/72ce16302c8c1f3ac62bff7dc915e765096a1585331874a9c7a65d13b4b7ff58.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": "7421be9dd57e0246d40bdda58ec49c8cabb5bc4dc2d01f505fd2850d3647a1f1", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "421e376e4b1a50857e2e9d0d8f3947614677bbc645584d3bab25cf1275941529", "generation_seconds_batch": 17.712037838995457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09801363945007324, "target_z": -0.18554687435472372, "ce": 6.181467056274414, "genuineness": 4.6203155517578125, "identity": 0.49147260189056396, "hypothesis": "Die Schlösser 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_Infatuation/7421be9dd57e0246d40bdda58ec49c8cabb5bc4dc2d01f505fd2850d3647a1f1.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "742eeca5f1ecb0b093655f97b666c63698c33a1b8bcf88d004aa05df0b79aa76", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "44a3d35428f7129f14ae679d33151f055c6acd53667473cac2a3dfefdd717b04", "generation_seconds_batch": 26.016467956011184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3792020082473755, "target_z": 0.3339843408003579, "ce": 5.335572719573975, "genuineness": 3.9801597595214844, "identity": 0.2922971546649933, "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_Infatuation/742eeca5f1ecb0b093655f97b666c63698c33a1b8bcf88d004aa05df0b79aa76.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "74b9b084605c5f11526047be70034a3eaaf0202094b55365be73abb6e8320fbc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8c161c6b63ba0b3b94bc2abd982f73f1656a92272dde9544138cab4e64fda092", "generation_seconds_batch": 25.13456731790211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34748905897140503, "target_z": 0.2753906402715383, "ce": 6.09409761428833, "genuineness": 4.381826400756836, "identity": 0.2234216034412384, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/74b9b084605c5f11526047be70034a3eaaf0202094b55365be73abb6e8320fbc.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "75327ee0219dd3e1d543c3ab1c2f06fea78f0bbc36f7c1ea809dbb45c4e4969a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b8702339039aa6743efdbc45e951324897ed7e24f00ea5bdef5226e8e7c76c8d", "generation_seconds_batch": 23.076234510052018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 6.24500846862793, "genuineness": 4.582659721374512, "identity": 0.7727698683738708, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/75327ee0219dd3e1d543c3ab1c2f06fea78f0bbc36f7c1ea809dbb45c4e4969a.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "75524be4367c785381dafe3285ed714227081d288aa4c6b0c8bb11c8dea4e439", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f1e2508ff53a72295987c27b480980b22d26500d0a050ddd2b51ebf94fc537c6", "generation_seconds_batch": 24.125889193965122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10964173078536987, "target_z": -0.16406249913963164, "ce": 5.387199878692627, "genuineness": 4.425758361816406, "identity": 0.3994045853614807, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. ¿podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/75524be4367c785381dafe3285ed714227081d288aa4c6b0c8bb11c8dea4e439.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "755b8fe67a179de1e3379f68a47539aabe93cea1c393a466483b8808696f54fa", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "609b09417d833b4880a99b9fd25c39991fc668084d9a8b04af77a7482b887378", "generation_seconds_batch": 17.901691467035562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6593332886695862, "target_z": 0.8515624509590037, "ce": 6.38797664642334, "genuineness": 4.457139015197754, "identity": 0.37097710371017456, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/755b8fe67a179de1e3379f68a47539aabe93cea1c393a466483b8808696f54fa.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "757402b041bb42d0dc5d7323265467ee941d7a76c1e95e326823118cb255159f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3ab0c534570fcdbf4969e316c9202f91fa0160e100fb44213828baa28cd5fa60", "generation_seconds_batch": 21.700005023973063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2380792796611786, "target_z": 0.0732421807245992, "ce": 5.2640886306762695, "genuineness": 4.507347106933594, "identity": 0.6424434185028076, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/757402b041bb42d0dc5d7323265467ee941d7a76c1e95e326823118cb255159f.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "75dfee9de47ff1b47c0a6a949cadc6c44adac3647c235f0830a85fcab147e765", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "105074bd62e88b50ed7176c14e1f6ffe91064fd064d5665b19b72110e02d30d1", "generation_seconds_batch": 25.848603095975704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4500276446342468, "target_z": 0.46484369708734613, "ce": 4.694201946258545, "genuineness": 4.149612903594971, "identity": 0.3219265341758728, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/75dfee9de47ff1b47c0a6a949cadc6c44adac3647c235f0830a85fcab147e765.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "76bf3068b53f742361b74a7b47cd4401d5a425ca4b694a3c8e672687a7be8891", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7cd0be67d7e637816f91377ca70eb0233bea80517ae551520b8b504999241054", "generation_seconds_batch": 23.240895787021145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10488478094339371, "target_z": -0.17285156798484827, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.6622034311294556, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/76bf3068b53f742361b74a7b47cd4401d5a425ca4b694a3c8e672687a7be8891.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "76c6012a9f7f2bfd04f8556dd13aef013554ffb7199aae75202359e7de028fc4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "534d4844587f90c24e2f63cc4873e78aeb1df48a4b874bf8a36aaea4497a8aa0", "generation_seconds_batch": 25.26687449403107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.025666967034339905, "target_z": -0.41406249913963167, "ce": 5.542081832885742, "genuineness": 4.406930446624756, "identity": 0.3837239146232605, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/76c6012a9f7f2bfd04f8556dd13aef013554ffb7199aae75202359e7de028fc4.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "76c62d3ca21118202cb3617b34b5d47dfdb88bfc1fd18b3e26673d053df6d9b9", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f91f800190f8f526a2a27fc27927f1b0cdf774f58fdd0187e79b6cc93b8a0212", "generation_seconds_batch": 17.372907920042053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02718798816204071, "target_z": -0.3164062581734994, "ce": 6.284721851348877, "genuineness": 4.18099308013916, "identity": 0.5130453109741211, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/76c62d3ca21118202cb3617b34b5d47dfdb88bfc1fd18b3e26673d053df6d9b9.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "76ced25cda3b962cc528307a30c9828c61c311a809d2afe3fb26c2d3261592bb", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6cb3571626a85ad2c69b38ca9f93191ece8b79f63a643bf1e118da8b05594eaf", "generation_seconds_batch": 25.452081073075533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01509597897529602, "target_z": -0.39453125645276266, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.6652658581733704, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/76ced25cda3b962cc528307a30c9828c61c311a809d2afe3fb26c2d3261592bb.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "76d49c1bc0ee34c8e39f88ae5072b73057cb7df7bf3a9ceb92622b4953008e67", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b8cbc40a5e0027ee45eea39cf007eb6f504eab06e13e92bf962ce5312b95b74f", "generation_seconds_batch": 23.591749171959236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 6.0146708488464355, "genuineness": 4.394378662109375, "identity": 0.6019713878631592, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/76d49c1bc0ee34c8e39f88ae5072b73057cb7df7bf3a9ceb92622b4953008e67.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": "76fe80bbef67f4fc94636db90bb0a38bf658860a2cf1b4ba6e43c8b5d0f9b9a5", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d18d3a45737dea2e334e7c566d3e2721d3fecb7d2638b8d6577717e9fde25468", "generation_seconds_batch": 24.85525384603534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08955684304237366, "target_z": -0.20117187951693385, "ce": 5.959072113037109, "genuineness": 4.582659721374512, "identity": 0.6642361283302307, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/76fe80bbef67f4fc94636db90bb0a38bf658860a2cf1b4ba6e43c8b5d0f9b9a5.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "77074ff9a1afdf513883760df80d285f964b6e3d25fbfc627d538c587d563f7e", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "362514115f3fabca10c67748db4b1ca035b1e472628497a9629f099af04b2e38", "generation_seconds_batch": 17.49466701899655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0018176138401031494, "target_z": -0.3632812461283424, "ce": 6.2767791748046875, "genuineness": 4.281409740447998, "identity": 0.5370323061943054, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/77074ff9a1afdf513883760df80d285f964b6e3d25fbfc627d538c587d563f7e.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": "7740b52c76bde3dfb40adc4dd432883f52cca314b44fcee0296c4324373979b4", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "af968032c14ead3597573a40f7a079da661ce53d60837e894bea0d180d699c0c", "generation_seconds_batch": 18.777234026929364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03412376344203949, "target_z": -0.42968750430184177, "ce": 5.927301406860352, "genuineness": 4.331617832183838, "identity": 0.7222301959991455, "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_Infatuation/7740b52c76bde3dfb40adc4dd432883f52cca314b44fcee0296c4324373979b4.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "671e8a134de442951c3650d6788654051668b70c142ff2c6ec767e04968034c6", "generation_seconds_batch": 16.812042430974543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05150127410888672, "target_z": -0.2714843752150921, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.7494896650314331, "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_Infatuation/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "77bfaf8a5d220d1c2c7da5e0e124abea43427aa2c6e144f355b305892eb62f3c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6a41ed717492ea4c1e0d75b7382da72db1a7cdfc73d9285878b0a0714f4a1b6b", "generation_seconds_batch": 17.590119868982583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04410158097743988, "target_z": -0.2851562478490791, "ce": 6.0146708488464355, "genuineness": 4.570107460021973, "identity": 0.6046230792999268, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/77bfaf8a5d220d1c2c7da5e0e124abea43427aa2c6e144f355b305892eb62f3c.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "77c6f558192994e5304a383f19df17d8d2f447c3def865901a9f7a5b501c17af", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dd50e74f2a74bbc436b85c051a63750e79e8126a8129823110664728d985cbf8", "generation_seconds_batch": 23.775733230053447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.018267273902893066, "target_z": -0.4003906265056446, "ce": 5.839932441711426, "genuineness": 4.381826400756836, "identity": 0.4808717966079712, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/77c6f558192994e5304a383f19df17d8d2f447c3def865901a9f7a5b501c17af.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "7818e0be6b32efab72c37826043d1d74e5ca190a49410c242ec9207b8ee87acd", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "72a8192e55ae639f9d143785e774e079105d64881738d46cb22ac503f3d33364", "generation_seconds_batch": 28.93170859501697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1886598914861679, "target_z": -0.018066413939542177, "ce": 6.157639026641846, "genuineness": 4.7834930419921875, "identity": 0.3856183886528015, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7818e0be6b32efab72c37826043d1d74e5ca190a49410c242ec9207b8ee87acd.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "789df538659b2b95096d0ad62f7eac72d6557082e00c4fcc2701aef61466b638", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "db1d19af4b920db2e6663b30f6839aa7511f54fbe1353e0fc81641bcb62ac9f0", "generation_seconds_batch": 17.4639029300306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4436850845813751, "target_z": 0.453125012045157, "ce": 5.696964263916016, "genuineness": 4.281409740447998, "identity": 0.45339781045913696, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/789df538659b2b95096d0ad62f7eac72d6557082e00c4fcc2701aef61466b638.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "78a8b643e854d4fa0ac15e4f879b98dd90ae0518c862842da140d7aad45ced08", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9ae5f412da5fc3220cd11613d49a5a45ed022c812bbd11871d74c709ab8e981", "generation_seconds_batch": 23.354029395035468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05890096724033356, "target_z": -0.25781250258110505, "ce": 6.435632705688477, "genuineness": 4.557555198669434, "identity": 0.5436495542526245, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/78a8b643e854d4fa0ac15e4f879b98dd90ae0518c862842da140d7aad45ced08.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "7945a28948d9d845ef39bf7546b1265dd78c693dec33190c725fef113b973e46", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a3ff5fb2c298554dfa8def414ed524327703f74c54ffa9f28aab5ec67cb0024a", "generation_seconds_batch": 25.885171959991567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008753374218940735, "target_z": -0.3828124888152114, "ce": 5.967014789581299, "genuineness": 4.293961524963379, "identity": 0.6500793695449829, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7945a28948d9d845ef39bf7546b1265dd78c693dec33190c725fef113b973e46.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16ab3d3cc95d72485c2e91a44a60db816eb6952c03af71513bb680c63fe5dc9d", "generation_seconds_batch": 21.565187492989935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03670188784599304, "target_z": -0.2988281204830661, "ce": 6.149696350097656, "genuineness": 4.494794845581055, "identity": 0.5876975655555725, "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_Infatuation/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "79c1fca6f41f909f63d3c1e218a12f1d4e79637fddda74ab6002895900441de4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57cbfebf222c451e197bc83f1e355f79659034e7baa3a58dc895e132df7ef290", "generation_seconds_batch": 24.03737466991879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05150127410888672, "target_z": -0.2714843752150921, "ce": 6.340320587158203, "genuineness": 4.457139015197754, "identity": 0.45309773087501526, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/79c1fca6f41f909f63d3c1e218a12f1d4e79637fddda74ab6002895900441de4.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "79cbc513e8cb6ee29973dfab1b276af9a91ebde88aa131f7dec2690f723fa585", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "403dd55aa1757cd389e5a45b2cf4ac640a3068d161fc6ee49301a622bebaa519", "generation_seconds_batch": 24.91757706401404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08004295080900192, "target_z": -0.2187500034414734, "ce": 6.133810997009277, "genuineness": 4.720732688903809, "identity": 0.39952582120895386, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/79cbc513e8cb6ee29973dfab1b276af9a91ebde88aa131f7dec2690f723fa585.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "79e633d302cecf44decc0b90d853071b6a49ebfc7482c9a528f1a59e98576808", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1b2d37d156b71587c537d7326f533ec1b1d8a42d3a62e0f956644d1b4962810d", "generation_seconds_batch": 23.568827050039545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6149351596832275, "target_z": 0.7695312702186563, "ce": 5.704906940460205, "genuineness": 4.582659721374512, "identity": 0.6334874629974365, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/79e633d302cecf44decc0b90d853071b6a49ebfc7482c9a528f1a59e98576808.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "7a214dc108fccd4b7ac330ca8a881ebd950b8ad2c866e183974dd0d103cedcac", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ac1df069b102522af693491930b2fcb70c717cd04d92c1b0e88f6a6cc5c176fb", "generation_seconds_batch": 23.708501091925427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.020381465554237366, "target_z": -0.40429686403030346, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.6320933699607849, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7a214dc108fccd4b7ac330ca8a881ebd950b8ad2c866e183974dd0d103cedcac.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "7a5fbcafd34f7e824fdb6d67c7b647227dd094e96c4c79c9c702275cc648c6be", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "690c04191fbad2c10ae0c9938375e5238d4be8de4fcc7eaebb73238c8ed04612", "generation_seconds_batch": 17.965882760006934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26529958844184875, "target_z": 0.12353515748677951, "ce": 5.935244083404541, "genuineness": 4.7081804275512695, "identity": 0.5739068984985352, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7a5fbcafd34f7e824fdb6d67c7b647227dd094e96c4c79c9c702275cc648c6be.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "7ad0b8727f1a9e0a319275d9d7974e4fb181ae16c373744750544851fc9c33c6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ce9ba7ec7182cfe8fcb50e56bcccd6d7eea24ca5c93881cbf10ede0ae10452c0", "generation_seconds_batch": 23.790547863929532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06577211618423462, "target_z": -0.24511718244533592, "ce": 5.8875885009765625, "genuineness": 4.582659721374512, "identity": 0.4295649528503418, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7ad0b8727f1a9e0a319275d9d7974e4fb181ae16c373744750544851fc9c33c6.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "7b19d0b0fa21f50016a8790c4b4b9a1c1e1b04b744f2ca39458bdd2e959e8d7e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "78d122dfad3f72ee2f5a0e3704d2001a7270aacfa170a2fe344e3dfa4d8e2357", "generation_seconds_batch": 24.60680480999872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42042890191078186, "target_z": 0.4101562616149728, "ce": 5.772419452667236, "genuineness": 4.758388519287109, "identity": 0.4407912492752075, "hypothesis": "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_Infatuation/7b19d0b0fa21f50016a8790c4b4b9a1c1e1b04b744f2ca39458bdd2e959e8d7e.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "7b411fa7310fc8759a00301734af7449cd902c40fe57cb84dd04da2909382082", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ad5c84a7636dacc9a08fe4dae009dba8cc84d8738e2f42b1237dca1ae5e7e75", "generation_seconds_batch": 24.44677006895654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12866951525211334, "target_z": -0.12890625129055253, "ce": 5.343515396118164, "genuineness": 4.293961524963379, "identity": 0.39927706122398376, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7b411fa7310fc8759a00301734af7449cd902c40fe57cb84dd04da2909382082.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "7b5da6a71317a387b33e92e784e4010a739f1ceca4acdd14b0b9b62ade15d3f7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "534867d38af4a7b395939150d0ebd2431eb4119ace05c13482cc3accda110ec2", "generation_seconds_batch": 24.492326147970743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5071110129356384, "target_z": 0.5703124681663708, "ce": 5.831989288330078, "genuineness": 4.231201171875, "identity": 0.35340821743011475, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7b5da6a71317a387b33e92e784e4010a739f1ceca4acdd14b0b9b62ade15d3f7.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "7c43e5bfaa5ae95da58271ed98908fb3e3d5ecd5285faf5cd47fda049fa59531", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8fb0e1b4b64ae758e84da513b358274bc1a04716c356122aed76e090de10c4d0", "generation_seconds_batch": 24.952231460949406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4775122404098511, "target_z": 0.5156249776304228, "ce": 6.229123115539551, "genuineness": 4.243753433227539, "identity": 0.2837980389595032, "hypothesis": "The 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_Infatuation/7c43e5bfaa5ae95da58271ed98908fb3e3d5ecd5285faf5cd47fda049fa59531.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "7c6a2851ab52e177e7fd6622bb4645688bfe5ffa5c265a98eb94b84bd299a0ef", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "439ce6e78c8993e492fe217b1c3796ad56f47b4d0f17b1a126c1502a0c6c5c69", "generation_seconds_batch": 28.44411278096959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07422890514135361, "target_z": -0.22949219104901947, "ce": 6.300607204437256, "genuineness": 4.143336772918701, "identity": 0.3856365382671356, "hypothesis": "The 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_Infatuation/7c6a2851ab52e177e7fd6622bb4645688bfe5ffa5c265a98eb94b84bd299a0ef.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "7c87ebf6d78cd02a4bdc524e1b5451452f1a507e3e56e8f83189b54ed75bdd28", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a02481bfddd18c8feebc71551cc7ecdca500f4436bbd2421c5adbac3525e974b", "generation_seconds_batch": 18.229127648985013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09642799198627472, "target_z": -0.1884765593811647, "ce": 5.982900142669678, "genuineness": 4.68307638168335, "identity": 0.6149344444274902, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7c87ebf6d78cd02a4bdc524e1b5451452f1a507e3e56e8f83189b54ed75bdd28.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "7cb3ed321f1f0554d084b5d0139d3227e9c9b4a6de99da0ff2fd705ae39778d5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "89ecf67cfbd65f73b061dbf9d356129380c81416b721ad52db8ae94556b699ff", "generation_seconds_batch": 25.33839057700243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05784386396408081, "target_z": -0.25976563510932815, "ce": 6.1020402908325195, "genuineness": 4.6956281661987305, "identity": 0.6238393783569336, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7cb3ed321f1f0554d084b5d0139d3227e9c9b4a6de99da0ff2fd705ae39778d5.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": "7cd04848b75306af077ba3135063a920a99bebf82d691120c1c985219e4221f5", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9dde586aa1c04f55c6ae0742a878db19e4f729be7ffe3b130660a0ed105d55a1", "generation_seconds_batch": 26.169258885085583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06312936544418335, "target_z": -0.25, "ce": 5.7406487464904785, "genuineness": 4.607763767242432, "identity": 0.549113392829895, "hypothesis": "Las llaves están en la mesa de la cocina, miren el cajón, y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7cd04848b75306af077ba3135063a920a99bebf82d691120c1c985219e4221f5.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "7d95ffe30829f62a9018847a582214fc453e80e2cd10036e34ab384b48d50707", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f735853f12898478910c491e53901e49912c57edbeb84c3c6fda7a822717cd87", "generation_seconds_batch": 23.367208495968953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09959928691387177, "target_z": -0.18261718932828275, "ce": 6.403861999511719, "genuineness": 4.300237655639648, "identity": 0.39064517617225647, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7d95ffe30829f62a9018847a582214fc453e80e2cd10036e34ab384b48d50707.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "7e29828aa2589d48b5cbbe7399039e53eae22aa63be98fc9834fe8d868a9b0ba", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d11ee12a51ef9f8f26585cb7a046e3e013c7c3d1b58d214cfa90e761579c7a98", "generation_seconds_batch": 25.92829769907985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31049057841300964, "target_z": 0.20703124956981583, "ce": 6.268836498260498, "genuineness": 4.425758361816406, "identity": 0.19954010844230652, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7e29828aa2589d48b5cbbe7399039e53eae22aa63be98fc9834fe8d868a9b0ba.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "7e73ab7b9c3b4633b1e30c349ecaa56fe93b4e551d2fe0d397b60c2bbce433e0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3aaa253918b709d4cfc9e1b7a7a5df61a579d97040ff2e15453a96605af74045", "generation_seconds_batch": 24.240906665916555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0066391825675964355, "target_z": -0.37890625129055255, "ce": 6.09409761428833, "genuineness": 4.532451152801514, "identity": 0.6911863684654236, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7e73ab7b9c3b4633b1e30c349ecaa56fe93b4e551d2fe0d397b60c2bbce433e0.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "7edbc0d34de4ec5535086e61bfaaca5147307f0d07bd581ebabb1e001f100942", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2457a79e0176825e7f0500cf24108b9cb264f980b2fac07cabb301f16941354d", "generation_seconds_batch": 24.76711841498036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1313122659921646, "target_z": -0.12402343373588845, "ce": 5.327630043029785, "genuineness": 4.545003414154053, "identity": 0.5008072257041931, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7edbc0d34de4ec5535086e61bfaaca5147307f0d07bd581ebabb1e001f100942.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "bfbb72eeac114660fcd290b8a41d145dacf4e250aabd1f84391b0aff8ba3c9a6", "generation_seconds_batch": 18.411073093069717, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03247348964214325, "target_z": -0.3066406230641712, "ce": 6.443574905395508, "genuineness": 4.287685871124268, "identity": 0.4683070182800293, "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_Infatuation/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "7f78799a266c9602ee9aca2aadc56ca7bcaf672d055068da0731a778de6a9e40", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc97c93a341b5d45462f2abc85baa372b5c716f121db683ad99b25df4934bfcd", "generation_seconds_batch": 24.44677006895654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 5.585766792297363, "genuineness": 4.356721878051758, "identity": 0.5822634696960449, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7f78799a266c9602ee9aca2aadc56ca7bcaf672d055068da0731a778de6a9e40.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "7f9a3e3f7c00827a17974701fb357b571b9570096beeba48183272060b2574a1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e36ff7e72dfeea5d8bcd545c2583bcb0b2f640619169a7480b8eb8945c7b0612", "generation_seconds_batch": 17.290859880042262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23332233726978302, "target_z": 0.06445312564527626, "ce": 5.689021587371826, "genuineness": 4.570107460021973, "identity": 0.30255386233329773, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7f9a3e3f7c00827a17974701fb357b571b9570096beeba48183272060b2574a1.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "7f9ba958d21a5cbda59bada083062112b206c3fe73b263e78b3db4a8090713aa", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "02bfc8fcdda6540dfee959e94b4aeff418064e1c7847fe286526447481c65a1f", "generation_seconds_batch": 23.321421329979785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03306666016578674, "target_z": -0.42773437177361867, "ce": 6.149696350097656, "genuineness": 4.369274139404297, "identity": 0.7078971266746521, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7f9ba958d21a5cbda59bada083062112b206c3fe73b263e78b3db4a8090713aa.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "7fd113ba072910683d1135429929c517be0ec6121ab0cdd709d77b2081f27ee9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "71a5b6717eb9179fbd69689505ff763e928ba283163345e2257d89e54cfa02d8", "generation_seconds_batch": 27.48518401395995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10647043585777283, "target_z": -0.1699218691925136, "ce": 5.387199878692627, "genuineness": 4.582659721374512, "identity": 0.22919109463691711, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/7fd113ba072910683d1135429929c517be0ec6121ab0cdd709d77b2081f27ee9.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "80bb089b87e42f6fbd893a766a704cdc05926c4b1a2e4d4ba5bcd257c31028a8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7d9a9f251cf3cd79eb1d9c399bdd1a81bdb2b7fcfffb82331fc375691696e86f", "generation_seconds_batch": 25.127563854912296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029302194714546204, "target_z": -0.3124999931170532, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.5634092092514038, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/80bb089b87e42f6fbd893a766a704cdc05926c4b1a2e4d4ba5bcd257c31028a8.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "e7725eb5815609f1e5e818cbbae9613d8d3c07736368df35d87ccf41aaa7cf7e", "generation_seconds_batch": 18.627726615057327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02507379651069641, "target_z": -0.32031249569815823, "ce": 6.316492557525635, "genuineness": 4.419482707977295, "identity": 0.6682704091072083, "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_Infatuation/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "8183872126311ef7713b65b23da02ed72901a9fb33d68c97916317e768ec255a", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0003e28bcdd4ed13a50f28fadf1eea7225ea2e6e886d51cd21f0635da7919cf5", "generation_seconds_batch": 17.633243234013207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1297266185283661, "target_z": -0.12695311876232943, "ce": 6.141753673553467, "genuineness": 4.193545341491699, "identity": 0.43480193614959717, "hypothesis": "The 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_Infatuation/8183872126311ef7713b65b23da02ed72901a9fb33d68c97916317e768ec255a.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "8288f7af925ced5e4edc0a20e9f55f62aa02f8f38f94e19b33bc9ae55dabf694", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b88ba971a82abdecd8ec995847e15b573644e5d78a48c7d91138d99580d7c743", "generation_seconds_batch": 23.755367582081817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003931805491447449, "target_z": -0.35937500860368354, "ce": 6.23706579208374, "genuineness": 4.632867813110352, "identity": 0.7071377038955688, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8288f7af925ced5e4edc0a20e9f55f62aa02f8f38f94e19b33bc9ae55dabf694.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "829b5b24da5bf2f509b68ba58b8e04bb71be84dfb2ac34b0a2ae81cf574fa1a9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c5b629db0dd7100df974565b72ea1d91df7abfb645468f476169f7e93b9c871c", "generation_seconds_batch": 17.250543317059055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08585699647665024, "target_z": -0.20800781583392738, "ce": 6.141753673553467, "genuineness": 3.9425034523010254, "identity": 0.3070811629295349, "hypothesis": "The 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_Infatuation/829b5b24da5bf2f509b68ba58b8e04bb71be84dfb2ac34b0a2ae81cf574fa1a9.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "839ace18f5954f9cc4114293e8e31c06a7d91059fb79ff838010e950a9b9f13a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b4ecb5c05ac8b1076341671a962db42ce7ba74e47ca9a7ecfc22013148641319", "generation_seconds_batch": 23.987548931967467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05361546576023102, "target_z": -0.26757813769043326, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.7115447521209717, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/839ace18f5954f9cc4114293e8e31c06a7d91059fb79ff838010e950a9b9f13a.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "83dbd3952604771059923e304e99594c7fcd724b2e38ea0fce59d2a5dc9a2577", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "114d1867b8e2f3c055b435cabacaa70ce7b4874fe0c932b07af94ecbcfe06480", "generation_seconds_batch": 17.250543317059055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04410158097743988, "target_z": -0.2851562478490791, "ce": 6.213237762451172, "genuineness": 3.9550557136535645, "identity": 0.2809803783893585, "hypothesis": "The 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_Infatuation/83dbd3952604771059923e304e99594c7fcd724b2e38ea0fce59d2a5dc9a2577.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "83dddd7f7db54f4842792d930647c8f353bf6e79c28f14b605672acd50d2de58", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "073475583181ff4b9f402b9547a3ae8e89c07c12c99d6de4fe02c65f30d764cf", "generation_seconds_batch": 21.865075169014744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.019324377179145813, "target_z": -0.4023437590338677, "ce": 6.300607204437256, "genuineness": 4.607763767242432, "identity": 0.7668316960334778, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/83dddd7f7db54f4842792d930647c8f353bf6e79c28f14b605672acd50d2de58.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "840283d5770703fa0a172f833c614cf03f13149a966060312bb204a9868b8c06", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6981b979f1c82f40efc3ecfe5474cb6e67b35bd48a6b82f338d96cabbb10de2b", "generation_seconds_batch": 17.295656098984182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03412376344203949, "target_z": -0.42968750430184177, "ce": 6.149696350097656, "genuineness": 4.595211505889893, "identity": 0.7527496218681335, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/840283d5770703fa0a172f833c614cf03f13149a966060312bb204a9868b8c06.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "85e3439d3449f715bad8d78db4a59c33003fb481c52c30ad970ce8eb0b589eab", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "951f3371a934a19d4777c6d6ea99609b0a8f47bbff2062a12664f811a077c7d5", "generation_seconds_batch": 23.141640392015688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11228448152542114, "target_z": -0.15917968158496756, "ce": 6.205295085906982, "genuineness": 4.7458367347717285, "identity": 0.5110863447189331, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/85e3439d3449f715bad8d78db4a59c33003fb481c52c30ad970ce8eb0b589eab.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "865a45f1fb3427b93558cae26bbf9cf31b647ee848eb42559f692b83b305d128", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8ec1ec549b36869f4efd512d9f9eb7e88ac4286d746af305ee473278be73f636", "generation_seconds_batch": 23.502638636971824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010867580771446228, "target_z": -0.3867187538716576, "ce": 5.927301406860352, "genuineness": 4.262581825256348, "identity": 0.4991772770881653, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/865a45f1fb3427b93558cae26bbf9cf31b647ee848eb42559f692b83b305d128.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "86c82454674a8b35d883f760a099d0c3a3418056e9b311433c3090a0e681762c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "888c4dd3ad307a72a3142ec5df6776c005d8130baf705604b65147895f26dd73", "generation_seconds_batch": 24.91757706401404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19648903608322144, "target_z": -0.0036010751933860277, "ce": 5.982900142669678, "genuineness": 4.796044826507568, "identity": 0.5915473699569702, "hypothesis": "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_Infatuation/86c82454674a8b35d883f760a099d0c3a3418056e9b311433c3090a0e681762c.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "87162476954f42727f4946ab0ff7ba4a5f47461dbd677302d73df59975dfe200", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "44727cfc2d1273876329d8f4a59bf307b181d1662a3927e7598802eaf7583869", "generation_seconds_batch": 23.591749171959236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0034678876399993896, "target_z": -0.3730468812376706, "ce": 5.95112943649292, "genuineness": 4.557555198669434, "identity": 0.21067258715629578, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/87162476954f42727f4946ab0ff7ba4a5f47461dbd677302d73df59975dfe200.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "8766909a55cc9ef248b86657aa4c675694a813abc0adfcc3849bdcc852a4229a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "73f1f4cad2dffa86def09431f77476040f9a1ed5bb80d474bfc00d3962d0094e", "generation_seconds_batch": 26.96136276505422, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10594188421964645, "target_z": -0.17089843545662517, "ce": 6.038498878479004, "genuineness": 4.846253395080566, "identity": 0.5714271664619446, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8766909a55cc9ef248b86657aa4c675694a813abc0adfcc3849bdcc852a4229a.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": "87c29837859c0fed2bc267eafef2003142a4dfafe7fdb0661dce5e9b698cc3b8", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9effa03dc017d7b7d8fd9f7cf4d9fa0fff6368548c640d84e88afb32b1321af8", "generation_seconds_batch": 17.179115866078064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054672569036483765, "target_z": -0.26562500516221016, "ce": 5.605623245239258, "genuineness": 4.545003414154053, "identity": 0.3520588278770447, "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_Infatuation/87c29837859c0fed2bc267eafef2003142a4dfafe7fdb0661dce5e9b698cc3b8.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "88115a079b9ae7ede706e53ffc0b05eda63d497b9b8947eba0872e6c237e3398", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9044069d8fbdc235bfd75b99a14568b27eafe3a50c90de55e7fa4707203ce981", "generation_seconds_batch": 24.240906665916555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016153067350387573, "target_z": -0.3964843614491984, "ce": 6.332377910614014, "genuineness": 4.570107460021973, "identity": 0.585966944694519, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/88115a079b9ae7ede706e53ffc0b05eda63d497b9b8947eba0872e6c237e3398.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": "881b40e3234eebb429ff62556bb4063a139c14f0df3a923d9f62431e922a765b", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f0c7b1d71cf2cef749c0af133972fb2bf3915d460985a914b0615f97b5e909e", "generation_seconds_batch": 24.85525384603534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05678677558898926, "target_z": -0.2617187401057639, "ce": 5.911416053771973, "genuineness": 4.582659721374512, "identity": 0.5908216238021851, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/881b40e3234eebb429ff62556bb4063a139c14f0df3a923d9f62431e922a765b.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "8827276f96bc0075638b9dc32d7691a2c5c65b7ab852160c79cc93d51e86a73c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c8c813266dd6d832209386e417e2c48ed6d8009a854befb440cf5896c6818c7c", "generation_seconds_batch": 24.17347156209871, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28617730736732483, "target_z": 0.16210939414319592, "ce": 5.792276382446289, "genuineness": 4.469690799713135, "identity": 0.4489753842353821, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8827276f96bc0075638b9dc32d7691a2c5c65b7ab852160c79cc93d51e86a73c.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "8853691a70746f37a2b0ca2fd4b57e30724544f7e1bf954ef1ec747b6d6ab4a1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6a435135cf9e727bea3544b73ebf0f4ecaac0173caed5626561afa29310c588e", "generation_seconds_batch": 26.827364495955408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14135470986366272, "target_z": -0.10546874354723733, "ce": 5.657250881195068, "genuineness": 4.632867813110352, "identity": 0.2769819498062134, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8853691a70746f37a2b0ca2fd4b57e30724544f7e1bf954ef1ec747b6d6ab4a1.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "88f66a86f3d79c5daaa492215ec58db4cbd7fa6e5529051d0dd40ff736ce1ace", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bf6a3f6c90203cfce3b44e1cbc2c30bad3910fadea5bf62d8cdc4b983cc9c333", "generation_seconds_batch": 24.057303398963995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15245425701141357, "target_z": -0.0849609208303631, "ce": 6.229123115539551, "genuineness": 4.432034492492676, "identity": 0.7205330729484558, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/88f66a86f3d79c5daaa492215ec58db4cbd7fa6e5529051d0dd40ff736ce1ace.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "8900c7854f57bada4795a083df59f1e74fca4c9666e16d8847f2f8618ea7e847", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "35c8057623079ed71baa73631d843c5f7f1ca3589ada20e3cffce1af607f640c", "generation_seconds_batch": 24.06297988409642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11756997555494308, "target_z": -0.14941406024153306, "ce": 6.221180438995361, "genuineness": 4.796044826507568, "identity": 0.4797605872154236, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8900c7854f57bada4795a083df59f1e74fca4c9666e16d8847f2f8618ea7e847.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "891ccf8f55e243a0718397998de7d3ea5121aea4568381187f3f2954c164a70b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c6d3d8041dac4c58866d88c378d14665b5fc503ddfcdd4a29f64ee6dbeebea8a", "generation_seconds_batch": 17.957940137013793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1603824943304062, "target_z": -0.07031249569815823, "ce": 5.95112943649292, "genuineness": 4.65797233581543, "identity": 0.4068160355091095, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/891ccf8f55e243a0718397998de7d3ea5121aea4568381187f3f2954c164a70b.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": "893b76e960b5d1fbb123aa741dc103da4e7c3d25ad619669046c3a02437bf121", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "bf67bc3ddc256945a48fb341f9b800fb55f92795d8e437d477f5503af23dd75a", "generation_seconds_batch": 19.97744996799156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10488478094339371, "target_z": -0.17285156798484827, "ce": 6.165581703186035, "genuineness": 4.519899368286133, "identity": 0.522163987159729, "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_Infatuation/893b76e960b5d1fbb123aa741dc103da4e7c3d25ad619669046c3a02437bf121.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "8a0508b9cd52d54147f1c3c398371ea54d0709086c0b4c0dcffe018f4e6fd9e1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "500ee509cd27dc33f991780eb08af00e093e39545273a235be7df2b73f70d07d", "generation_seconds_batch": 24.681338221998885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.403861999511719, "genuineness": 4.7458367347717285, "identity": 0.5689266324043274, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8a0508b9cd52d54147f1c3c398371ea54d0709086c0b4c0dcffe018f4e6fd9e1.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "8a08748c2fdf6de0db6ac191bf4cd8c10de0d3734368ae6389bd83aab5c00fa5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d8916abf132c70d300599a4fb140a26ac17843c6f98ecb62aa587574a8357fb9", "generation_seconds_batch": 17.234122215071693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10858462750911713, "target_z": -0.16601563166785477, "ce": 6.41180419921875, "genuineness": 4.3127899169921875, "identity": 0.32135793566703796, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8a08748c2fdf6de0db6ac191bf4cd8c10de0d3734368ae6389bd83aab5c00fa5.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": "8a1d741409763dc439d01616ead313a8fa1f44df804e506e23fd594364864581", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62fcc22825266f4767569023fc2463179e17bf9d771fbaca84a1ae6a2f70b5e6", "generation_seconds_batch": 24.948952112928964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018731191754341125, "target_z": -0.33203126333570954, "ce": 5.649308204650879, "genuineness": 4.532451152801514, "identity": 0.7722464799880981, "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_Infatuation/8a1d741409763dc439d01616ead313a8fa1f44df804e506e23fd594364864581.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "8a5a110493d4ef43fcbcb07efeaa48f8f67e6770b63e8b2bf75cb06fe9f6d242", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d3081cb3020d3836201da16c894dd9bd82c81a7a6bc9384d3b705b56074f0eb3", "generation_seconds_batch": 25.812623452045955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06471501290798187, "target_z": -0.24707031497355902, "ce": 5.967014789581299, "genuineness": 4.557555198669434, "identity": 0.6891831755638123, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8a5a110493d4ef43fcbcb07efeaa48f8f67e6770b63e8b2bf75cb06fe9f6d242.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "8a66df4d45de37a6f98759528641256bd05272ee93313d987b4d99064b766057", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "db445ba431cfb89e2f0c1d83cf59638084a3f42550821bb211a6927fc57e9031", "generation_seconds_batch": 23.648502427968197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011331498622894287, "target_z": -0.34570313596969654, "ce": 6.0146708488464355, "genuineness": 4.444586753845215, "identity": 0.7490518093109131, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8a66df4d45de37a6f98759528641256bd05272ee93313d987b4d99064b766057.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "8b12c11d419d80764eb020f1d822c78f1b7786e5bd797f86627a1f13be4bfe5a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5e2e02f4b132c657dd9bc2a1ca19926d50d7d55cd4d5ae4af71d1a52a644af13", "generation_seconds_batch": 23.589804211980663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05890096724033356, "target_z": -0.25781250258110505, "ce": 5.792276382446289, "genuineness": 4.570107460021973, "identity": 0.4872813820838928, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8b12c11d419d80764eb020f1d822c78f1b7786e5bd797f86627a1f13be4bfe5a.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": "8ca5e16bc0b6430f0d93b8e79d36f9fab2ef1f2f4cd07704de1cea7dd3dff304", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0168709de28ec590e98624f5faca93af50a5916d5a675fa0ec4528c855ab34e2", "generation_seconds_batch": 16.88044021592941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4479134678840637, "target_z": 0.4609374870944747, "ce": 6.284721851348877, "genuineness": 4.243753433227539, "identity": 0.5334322452545166, "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_Infatuation/8ca5e16bc0b6430f0d93b8e79d36f9fab2ef1f2f4cd07704de1cea7dd3dff304.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "8d45afbf1b1a6e23031f70c13a0b3b7da3f4ad5e584195d59a6963dd7bb8c1f7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e4acb5d75baa71d0ec903e7ce0da483e738a03ef40cbec3104d987c34e64bf63", "generation_seconds_batch": 25.372966546099633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23702219128608704, "target_z": 0.07128907572816347, "ce": 6.0305562019348145, "genuineness": 3.9550557136535645, "identity": 0.2908005714416504, "hypothesis": "The 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_Infatuation/8d45afbf1b1a6e23031f70c13a0b3b7da3f4ad5e584195d59a6963dd7bb8c1f7.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "8df8c05d835a7ae25532df6a3f06a5212934e1c7c7ded5bc703f627cd3c6878d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "48e7ab39f5682002ccf8c59a57028728f7bd76a529acfc2da5b388b5bf656771", "generation_seconds_batch": 17.687529076007195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2578998804092407, "target_z": 0.10986325732100512, "ce": 5.6413655281066895, "genuineness": 4.68307638168335, "identity": 0.46425148844718933, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8df8c05d835a7ae25532df6a3f06a5212934e1c7c7ded5bc703f627cd3c6878d.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "8e1c449c7be2de5d11d067ce77a264c1e873b8e29f005d39b74158d11b58e31b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "06797bf03e125c32a76880e89b9794ec4c3e5d27b2ada14ae2c8bbd07a04d0f5", "generation_seconds_batch": 25.731898033060133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19420966506004333, "target_z": -0.007812502581105066, "ce": 5.593709468841553, "genuineness": 4.507347106933594, "identity": 0.7793309688568115, "hypothesis": "J'ai trouvé la 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_Infatuation/8e1c449c7be2de5d11d067ce77a264c1e873b8e29f005d39b74158d11b58e31b.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "8e4125d017d70c27314032995c945b6ae7cf8b81462c827015c5d5dfe1bf3df9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4255c1dcb0254d058f5e50ccf22499efcf833d2e5450156e2837baf0fc24fbf1", "generation_seconds_batch": 23.142438968992792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0906139463186264, "target_z": -0.19921874698871075, "ce": 6.332377910614014, "genuineness": 4.356721878051758, "identity": 0.494194358587265, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8e4125d017d70c27314032995c945b6ae7cf8b81462c827015c5d5dfe1bf3df9.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": "8e4a7b314b3254e54c96be51a75f74f7c6d3553505eb203cac0cda082c020830", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "43eccc4215ad02521b480a1fad5a887d6fffd995120b83cdf72cbd45022fc306", "generation_seconds_batch": 24.04342711006757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11968417465686798, "target_z": -0.14550780895098053, "ce": 6.078212261199951, "genuineness": 4.532451152801514, "identity": 0.7720332145690918, "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_Infatuation/8e4a7b314b3254e54c96be51a75f74f7c6d3553505eb203cac0cda082c020830.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "8e60a89d8de7ad5646cfb7d2ab0f124cef73893363cc4cf40c79178d060b7096", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7399b4c1e0e143fe930785c2cdb650e6c28bb0b44e8e98efa3eca36dd94f58da", "generation_seconds_batch": 22.93575245095417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 6.324435234069824, "genuineness": 4.645420074462891, "identity": 0.5911165475845337, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8e60a89d8de7ad5646cfb7d2ab0f124cef73893363cc4cf40c79178d060b7096.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "8e65feae1bc9f5e947abef95d870028614377e4b0be82e34e9e9f37565885110", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "92db673e44864939c08d856eb46e6f5954f9f7418f02b0a4265052bca132bf10", "generation_seconds_batch": 26.043136209016666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003931805491447449, "target_z": -0.35937500860368354, "ce": 6.284721851348877, "genuineness": 4.595211505889893, "identity": 0.5555526614189148, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8e65feae1bc9f5e947abef95d870028614377e4b0be82e34e9e9f37565885110.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "8edf41884053bb31b0ede3ff7b32e856d364e016ec1b570ac6677f403b325707", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8f89bb285cc4701158e31d96f8b3b0915062e5153ee5c3d059d6c31321d32846", "generation_seconds_batch": 26.867222398053855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.471169650554657, "target_z": 0.5039062375246588, "ce": 5.847874641418457, "genuineness": 4.011539936065674, "identity": 0.37863725423812866, "hypothesis": "The 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_Infatuation/8edf41884053bb31b0ede3ff7b32e856d364e016ec1b570ac6677f403b325707.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "8ef5461cf409b252f2204b307777b517c21c6fc5b842700e045a84465bf39356", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4cfea853c132063c004ba2de90b5e04d3c1215109441229926f29860fbebd3f8", "generation_seconds_batch": 24.177380174049176, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06312936544418335, "target_z": -0.25, "ce": 6.070269584655762, "genuineness": 4.068024158477783, "identity": 0.42100852727890015, "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_Infatuation/8ef5461cf409b252f2204b307777b517c21c6fc5b842700e045a84465bf39356.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "8f16e23a64b808bddc61e271077a1e3f5a65dc74c5828e1234c9a659077767ad", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c59f432394dba6610a14194614343e56ac42f5ccc6ac6ee29d1fe9f6781a8c77", "generation_seconds_batch": 23.626117254025303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.054672569036483765, "target_z": -0.26562500516221016, "ce": 6.09409761428833, "genuineness": 4.055472373962402, "identity": 0.4870944023132324, "hypothesis": "The 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_Infatuation/8f16e23a64b808bddc61e271077a1e3f5a65dc74c5828e1234c9a659077767ad.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": "8f1ce6f09d3f160fd8f1639e728b78023cdd146424661de6a0b22ee46032b0ff", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21e0d3991413d704d74a7c11b58037b2f7341df58c79b6ab0916b33774acfbb6", "generation_seconds_batch": 17.6791376179317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3115476667881012, "target_z": 0.20898435456625156, "ce": 5.8875885009765625, "genuineness": 4.394378662109375, "identity": 0.5066882371902466, "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_Infatuation/8f1ce6f09d3f160fd8f1639e728b78023cdd146424661de6a0b22ee46032b0ff.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "8faee60588d41a0881056fc899bf40c764d702e24cbcd8dbd09e6dc3cc005bd9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "162023b4d3b1a2813c4b1d72f4cf64cefc80f1fa45721520e6ab86110e5c18ce", "generation_seconds_batch": 23.765262320055626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.009810477495193481, "target_z": -0.3847656213434345, "ce": 6.125868320465088, "genuineness": 4.432034492492676, "identity": 0.7061035633087158, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8faee60588d41a0881056fc899bf40c764d702e24cbcd8dbd09e6dc3cc005bd9.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "8fbedecec28a2031527212fd3652635bb151027961e3650e97b14d4dc1c64659", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afd80dd88979431f13e8377b952160e8c9a82bcc717837d07f5c793229f94bb6", "generation_seconds_batch": 17.511477167950943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1652715802192688, "target_z": -0.06127928872838714, "ce": 6.133810997009277, "genuineness": 4.632867813110352, "identity": 0.5200610160827637, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/8fbedecec28a2031527212fd3652635bb151027961e3650e97b14d4dc1c64659.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "900572683bb2ffbd4b265b7dfd31dd6e3848788c308dda53130f28590104bc77", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4e21f86bb0758ad7472044376ac4f7ad312bea6bc780b26c207d720ad1aac75", "generation_seconds_batch": 22.65012021898292, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04832997918128967, "target_z": -0.27734374526797406, "ce": 6.062326908111572, "genuineness": 4.758388519287109, "identity": 0.7685397863388062, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/900572683bb2ffbd4b265b7dfd31dd6e3848788c308dda53130f28590104bc77.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "907f3ef01c44973adc8332902fdf41b5f75806936ee3d4b54b96e681dbfe6633", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e9878ac6ed1d5b271fad67db4cfc4742acfa68c63e2af9a40aa661b494e736c4", "generation_seconds_batch": 26.53300917893648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6339629292488098, "target_z": 0.8046874905359481, "ce": 5.43088436126709, "genuineness": 4.532451152801514, "identity": 0.44937658309936523, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/907f3ef01c44973adc8332902fdf41b5f75806936ee3d4b54b96e681dbfe6633.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "9096264133eb8b35d4f26625a9c4d633dd4b0f00fd5040283217c79cc8a180d2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8e28c04ebb9a1f9a4f42ac0981662329c0dfaee220ccf5f7e11dd181fbe5f5a5", "generation_seconds_batch": 22.940151832066476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17095348238945007, "target_z": -0.050781253011289246, "ce": 5.414999485015869, "genuineness": 4.21237325668335, "identity": 0.23508256673812866, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9096264133eb8b35d4f26625a9c4d633dd4b0f00fd5040283217c79cc8a180d2.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "90c3f93f665cd79799be4d7c2c17297455ca4271beaa29ba03596039b1e62924", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "750a13658032df7a03d5d1d495daa41c664b17a8996156163517dd51c87b4332", "generation_seconds_batch": 24.59163495793473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16804645955562592, "target_z": -0.056152346815062266, "ce": 6.395919322967529, "genuineness": 4.557555198669434, "identity": 0.5192444920539856, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/90c3f93f665cd79799be4d7c2c17297455ca4271beaa29ba03596039b1e62924.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "90d19f2328365d4b4bf8468c4618e3d5d90cd30d036095dd92795e9065570226", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4b8bc754a4a310f1c05dfe2b2e76117ac2b3031dc92753026e1482b5d0c7b43e", "generation_seconds_batch": 26.407272892072797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033530592918395996, "target_z": -0.30468749053594807, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.5948826670646667, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/90d19f2328365d4b4bf8468c4618e3d5d90cd30d036095dd92795e9065570226.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "90ddbbd90112cac5a3a8566f7a5b1ddea9899cc57c3200fab75f8b2c0314abcf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2b0030b49e043fe282b4234166f6347b3dad142c394742847c2ec94aecec3139", "generation_seconds_batch": 23.076234510052018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03412376344203949, "target_z": -0.42968750430184177, "ce": 6.062326908111572, "genuineness": 4.218649387359619, "identity": 0.6051994562149048, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/90ddbbd90112cac5a3a8566f7a5b1ddea9899cc57c3200fab75f8b2c0314abcf.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "914fdbe851861c65a2cbb28b53abec3f3fbd62496fc0a2dac8ab4e6e96167135", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7435815fb1d6b26378567e2f6ef6e6236a05103b01ecdc30cf0f579917d83171", "generation_seconds_batch": 25.724155250936747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004524990916252136, "target_z": -0.3750000137658937, "ce": 6.165581703186035, "genuineness": 4.582659721374512, "identity": 0.4538124203681946, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/914fdbe851861c65a2cbb28b53abec3f3fbd62496fc0a2dac8ab4e6e96167135.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "915ccd1b24ae066aea3dd31ca2612c1b7d64116eb8a8223fcfdcf0093d55496e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ddfb392f3234a50371e97ec3068f40fe4b55c8547c513e8ef172420f6cc2367", "generation_seconds_batch": 17.475542593980208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024016693234443665, "target_z": -0.32226562822638133, "ce": 5.77639102935791, "genuineness": 4.243753433227539, "identity": 0.5371806025505066, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/915ccd1b24ae066aea3dd31ca2612c1b7d64116eb8a8223fcfdcf0093d55496e.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "91d4ca090bd15aa4bfc986f745cd6326ca6f76a5501ab403b42c806d05bdb157", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "62fb791583cf37523f8517bfa89137a9a5a9b14c0c58dd34fa1ce76ca75027bc", "generation_seconds_batch": 18.21480709698517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10329913347959518, "target_z": -0.17578125301128925, "ce": 5.506340026855469, "genuineness": 4.7458367347717285, "identity": 0.7353551387786865, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/91d4ca090bd15aa4bfc986f745cd6326ca6f76a5501ab403b42c806d05bdb157.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "926046b572e3282cd406ece5767fe8490fbf4e9bd395276c121b7af0d341f19c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9542b41cca46adb0e505c374f8023acaefd13db7b83f932cce2124a6209b91e4", "generation_seconds_batch": 23.768604438053444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25499287247657776, "target_z": 0.10449219104901947, "ce": 5.990842819213867, "genuineness": 4.532451152801514, "identity": 0.7802338600158691, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/926046b572e3282cd406ece5767fe8490fbf4e9bd395276c121b7af0d341f19c.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "9317e052ecc3ab0f0755df2e08e65a3ebca34882ed88a89a026d37d6eef41547", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7fbca043dcea5482b7835e5df37b30922b200da946ed8a0ead6ac28e3048897f", "generation_seconds_batch": 26.53300917893648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2888200283050537, "target_z": 0.16699215663428524, "ce": 4.8580193519592285, "genuineness": 4.1998209953308105, "identity": 0.4075182378292084, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9317e052ecc3ab0f0755df2e08e65a3ebca34882ed88a89a026d37d6eef41547.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": "9341e2c509446fdeb4eb01e8973a08d4207f328c2af37774789020d50c7b005f", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "070c516bd48566c796aaaf8409e4c3033bf7087c0ea980b6737aea46db38d421", "generation_seconds_batch": 24.085700594005175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.020381465554237366, "target_z": -0.40429686403030346, "ce": 6.125868320465088, "genuineness": 4.111956596374512, "identity": 0.6894079446792603, "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_Infatuation/9341e2c509446fdeb4eb01e8973a08d4207f328c2af37774789020d50c7b005f.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "93629c57e83aece67d157a489a5a98fdd3d45f42087202fa4c01fb240129195c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3693fd55c08d7e9fd6b8f07ce28ddc20793fd9faa861de4ad73f637894ca3dd3", "generation_seconds_batch": 22.948762655025348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003931805491447449, "target_z": -0.35937500860368354, "ce": 5.3792572021484375, "genuineness": 4.532451152801514, "identity": 0.2468007653951645, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/93629c57e83aece67d157a489a5a98fdd3d45f42087202fa4c01fb240129195c.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "93709a1ac5311b1dba1e80f807ae46c2e2ea5d62991682287fab3dce559eb2e2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ee9f20dafe858238dbc82bce47d9e12e345cbfff0448c01066eb0422420077b9", "generation_seconds_batch": 17.54722907708492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 6.0305562019348145, "genuineness": 4.68307638168335, "identity": 0.7130277156829834, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/93709a1ac5311b1dba1e80f807ae46c2e2ea5d62991682287fab3dce559eb2e2.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "939fffc8323496990893717207695d10d5e884f7dd4506ad2437cce8fc27f487", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "822dfc26d98d6341356a0ad01eb55fb37ef9ffeabf7b1f5ea9f42030ebd73ea3", "generation_seconds_batch": 23.49973385501653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10805608332157135, "target_z": -0.16699218416607262, "ce": 5.967014789581299, "genuineness": 4.494794845581055, "identity": 0.46062958240509033, "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_Infatuation/939fffc8323496990893717207695d10d5e884f7dd4506ad2437cce8fc27f487.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "94df233639e08fb75d5333ba8359bcf93163dd61edaa3d0cd84ab125a9bbf8b6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e38f7fae5ba52f1acb0ac7ba4988e6b1b1591d49ed6267e3f9cd906925392361", "generation_seconds_batch": 22.83276259608101, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012981772422790527, "target_z": -0.39062499139631646, "ce": 5.5738525390625, "genuineness": 3.9927117824554443, "identity": 0.5511031150817871, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ramen. 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_Infatuation/94df233639e08fb75d5333ba8359bcf93163dd61edaa3d0cd84ab125a9bbf8b6.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "9503548a04e23516743d693a38127304640b0922e68c54de99fd26ed922d6b36", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7c43f51757bbdd66a8383e48bd98859d4f3dd093aba5dea26e88ffb0f789c3ba", "generation_seconds_batch": 26.141676479019225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01509597897529602, "target_z": -0.39453125645276266, "ce": 6.125868320465088, "genuineness": 4.457139015197754, "identity": 0.5421014428138733, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9503548a04e23516743d693a38127304640b0922e68c54de99fd26ed922d6b36.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "9543fe83e26790e940c5e9ba570db948464b50ba3a0efce2bc230251491b5dc2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "86af3ca322c49661ce82d0e8fb2e1785852ca30e515c2e5957fec1d0300b2c39", "generation_seconds_batch": 23.765262320055626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011331498622894287, "target_z": -0.34570313596969654, "ce": 6.070269584655762, "genuineness": 4.582659721374512, "identity": 0.5288859009742737, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9543fe83e26790e940c5e9ba570db948464b50ba3a0efce2bc230251491b5dc2.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "9546bc543eda282dfb26c58b8baf3329374eae1a3d24f3fa61d7c7555d9c0257", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0cb7eb1010b4e1dc26f4203a2434668a94fb7092e92173f4cecb18a42f4ddeec", "generation_seconds_batch": 26.84728305891622, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07211470603942871, "target_z": -0.233398442339572, "ce": 5.5817952156066895, "genuineness": 4.457139015197754, "identity": 0.5034090280532837, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9546bc543eda282dfb26c58b8baf3329374eae1a3d24f3fa61d7c7555d9c0257.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": "9642b1bbfc1cd0b6f791aa073449199c07ccb971982be2e5c1dcdb0220e1ac1e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "186446cbfd00d7bb1f6e0381b1bd1bccb8ae394d4f8d66b9cc6943b315738a3d", "generation_seconds_batch": 25.965201972983778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4690554738044739, "target_z": 0.5000000275317874, "ce": 6.109982967376709, "genuineness": 4.256305694580078, "identity": 0.37068673968315125, "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_Infatuation/9642b1bbfc1cd0b6f791aa073449199c07ccb971982be2e5c1dcdb0220e1ac1e.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "969f426de417f7e856da3cf884d0bc657944703c34a1a966f8a29f0ff136624d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cf636fa66984c7eda2c069e44e3daeea20b6c2e86b86b780d80261c725d47994", "generation_seconds_batch": 22.532487914082594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0805715024471283, "target_z": -0.21777343717736186, "ce": 5.577824115753174, "genuineness": 4.7834930419921875, "identity": 0.7614116668701172, "hypothesis": "J'ai trouvé la 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_Infatuation/969f426de417f7e856da3cf884d0bc657944703c34a1a966f8a29f0ff136624d.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "96ed095e854c057f21bc4ca75e72fe5afb19494192e506cde9ec05c76fc2716a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd4aab5323316fe55e4c120582909d0bdfed8ebb6d1d493c199a376cc9311a70", "generation_seconds_batch": 25.055259536020458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25763562321662903, "target_z": 0.10937500860368356, "ce": 5.661221981048584, "genuineness": 4.369274139404297, "identity": 0.33889269828796387, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/96ed095e854c057f21bc4ca75e72fe5afb19494192e506cde9ec05c76fc2716a.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "970968746e764c8b64a2155250c427ba91dde0057e4bd83e6b8531d32a7c77d8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b1fb840cb1b169950564f6c4fa2eb9e90437e49f02c91f1882992ceb79bcabbc", "generation_seconds_batch": 24.03287954197731, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.078212261199951, "genuineness": 4.419482707977295, "identity": 0.5483758449554443, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het houden raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/970968746e764c8b64a2155250c427ba91dde0057e4bd83e6b8531d32a7c77d8.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "970d481d5de7f30e37fd9ac7e515f9c82d5138cf833c43fb9670fd2d86cf4e13", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d1bd60353f796a000ba2e8796c320b9c18a44fd28e701891cccfe1d45ac9320f", "generation_seconds_batch": 18.934529917081818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0663006603717804, "target_z": -0.24414062994711805, "ce": 6.149696350097656, "genuineness": 4.595211505889893, "identity": 0.6182656288146973, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/970d481d5de7f30e37fd9ac7e515f9c82d5138cf833c43fb9670fd2d86cf4e13.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": "971a739d17079c1b72cfe87d948862a21680a4733345546d0640a9194b62f7a0", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "47d0ceb5e8960e4d1fc44ff6c668917c97f1297b1c8cbfc1a1d9cb7200d30f3b", "generation_seconds_batch": 17.106556372949854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31419041752815247, "target_z": 0.21386717212091563, "ce": 6.125868320465088, "genuineness": 4.758388519287109, "identity": 0.676804780960083, "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_Infatuation/971a739d17079c1b72cfe87d948862a21680a4733345546d0640a9194b62f7a0.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "97a0027dea9285da1bddc16574c288902893484af41a06959efff4c9bc31c42b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d26ff5f4496b5f127071deaafc932a83a4d4e9a290db9360d20e9cb883e62db2", "generation_seconds_batch": 23.557780656032264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08532845228910446, "target_z": -0.20898436833214523, "ce": 6.117925643920898, "genuineness": 4.432034492492676, "identity": 0.8261390924453735, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/97a0027dea9285da1bddc16574c288902893484af41a06959efff4c9bc31c42b.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "97e16c8fea8a1c43f644d5507b6860d01eaeffd4ed0385856c39cc7101ae5593", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1dd7b053c025710172178dcdbf0bba280b6941d876d1337b3c03497541bd71e2", "generation_seconds_batch": 24.140048130066134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014502808451652527, "target_z": -0.3398437383850272, "ce": 6.054384231567383, "genuineness": 4.293961524963379, "identity": 0.5283557176589966, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/97e16c8fea8a1c43f644d5507b6860d01eaeffd4ed0385856c39cc7101ae5593.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "98495f0f0e0bd64ee30ea40506a701df1230656baa73049afd9916388e94d35e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b98554047efd5f1759deaec037582e70a446e520b0555d782361ee2d480644f8", "generation_seconds_batch": 24.71873175993096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19579531252384186, "target_z": -0.004882817554664088, "ce": 6.062326908111572, "genuineness": 4.720732688903809, "identity": 0.46581506729125977, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/98495f0f0e0bd64ee30ea40506a701df1230656baa73049afd9916388e94d35e.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "987ceb2ed350b12698558c138ab46e0357ac0b4700c2793335f6938ed4e4b6d0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0e7162e5bdda39c07053ff314de27ad7230e263599d8da9dde80ce4e1632da69", "generation_seconds_batch": 26.073071796097793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5747653841972351, "target_z": 0.6953125094640519, "ce": 5.6532793045043945, "genuineness": 4.306513786315918, "identity": 0.37152427434921265, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/987ceb2ed350b12698558c138ab46e0357ac0b4700c2793335f6938ed4e4b6d0.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "98d1e6c98186d7162580d3dd297be6733eb79303c57eee686800a6f8adb234be", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a2a369d37ed521ad59e5859099e3f2948f817db6bb46d1eb3274b024f10c843f", "generation_seconds_batch": 17.511477167950943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006046012043952942, "target_z": -0.35546874354723734, "ce": 5.879645347595215, "genuineness": 4.482243061065674, "identity": 0.08352777361869812, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/98d1e6c98186d7162580d3dd297be6733eb79303c57eee686800a6f8adb234be.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "98ec4f3200813ff5f89c2192bd8860799e2eeae30fa2fd98846e75508a3692a1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f3d8d4ac4a495cc38c08d4a24cd398cea406199b2bc2cf1e255f2365012d8913", "generation_seconds_batch": 18.81931687996257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05784386396408081, "target_z": -0.25976563510932815, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.5535966157913208, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/98ec4f3200813ff5f89c2192bd8860799e2eeae30fa2fd98846e75508a3692a1.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "9918b828cf846b892eb9fb5a58d52ae1d7148d8cbcabb9dd440b0cd85b0384e9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9fb4fd201a52515842feb8726560165e11f045029fb726e91f3e256cf4f35e6d", "generation_seconds_batch": 24.493328273994848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2925198972225189, "target_z": 0.17382813424895982, "ce": 5.831989288330078, "genuineness": 4.6956281661987305, "identity": 0.8191827535629272, "hypothesis": "La porte 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_Infatuation/9918b828cf846b892eb9fb5a58d52ae1d7148d8cbcabb9dd440b0cd85b0384e9.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "9812c5ab05018894f1a9445ed2db330a110e63460ce90373c8a721a2f2ed8524", "generation_seconds_batch": 18.87178535910789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033530592918395996, "target_z": -0.30468749053594807, "ce": 6.348263263702393, "genuineness": 4.632867813110352, "identity": 0.6848306655883789, "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_Infatuation/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "9a3941eea16e7275d2b54bd9a4c04b40d1fd506c12303c7898c1bbadd82066a7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "97fb3db708990461fbf637f14245c5cf331164bbd059870789191d7f8a116870", "generation_seconds_batch": 24.977512422017753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04410158097743988, "target_z": -0.2851562478490791, "ce": 6.1894097328186035, "genuineness": 4.6956281661987305, "identity": 0.41429805755615234, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9a3941eea16e7275d2b54bd9a4c04b40d1fd506c12303c7898c1bbadd82066a7.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": "9a49c88339ccf85a99263a22b60147b9f9d5bac9f7f0688e6a2da806fb257eaa", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2948c2f8aa4c6a687c07456a84b0dfb2a141e20992f863457d2245598b535a23", "generation_seconds_batch": 17.100723174982704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25499287247657776, "target_z": 0.10449219104901947, "ce": 6.149696350097656, "genuineness": 4.369274139404297, "identity": 0.6983494758605957, "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_Infatuation/9a49c88339ccf85a99263a22b60147b9f9d5bac9f7f0688e6a2da806fb257eaa.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": "9a8b2bc76cf10094ef4ac19415644567afff8ed68a5eaf6db61873cbc59d5990", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bf9012481f3440a0ea87c9e70d7511d524942d480022bdefc93a7bd35fbe7044", "generation_seconds_batch": 17.100723174982704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32476142048835754, "target_z": 0.233398442339572, "ce": 6.260893821716309, "genuineness": 4.231201171875, "identity": 0.48125189542770386, "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_Infatuation/9a8b2bc76cf10094ef4ac19415644567afff8ed68a5eaf6db61873cbc59d5990.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "9acaf5e58c9afb147190ffcedd5364d13d3ea9aee94b614500bbdccf074f1bdf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fa4c77b24a42fa47b6040403f4d1acf9f4b0006e0e84b9116836300e2c967809", "generation_seconds_batch": 23.137905756011605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03775899112224579, "target_z": -0.296874987954843, "ce": 6.300607204437256, "genuineness": 3.9550557136535645, "identity": 0.30181366205215454, "hypothesis": "The 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_Infatuation/9acaf5e58c9afb147190ffcedd5364d13d3ea9aee94b614500bbdccf074f1bdf.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "9b07c8ea9fb35ebe92890c8a05ff9b7389e86afb38fe9e1bcedcd9afc38d69d4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a0cf88abf4cee41c9c629fdca801db28679f780559948464fa9b62b06d0a2cb7", "generation_seconds_batch": 17.613793781027198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 6.252951145172119, "genuineness": 4.68307638168335, "identity": 0.37296080589294434, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9b07c8ea9fb35ebe92890c8a05ff9b7389e86afb38fe9e1bcedcd9afc38d69d4.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": "9b1ee05849af72c03de3404e6542c2a0810be62ad7141ed079785260612cd0c4", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6ab960f67fd009c032932454b5bd87f7388a580058ad80d1307525c29f32472", "generation_seconds_batch": 17.533707518014126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029302194714546204, "target_z": -0.3124999931170532, "ce": 5.538110733032227, "genuineness": 4.406930446624756, "identity": 0.5347766876220703, "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_Infatuation/9b1ee05849af72c03de3404e6542c2a0810be62ad7141ed079785260612cd0c4.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "9b78e95664caf77ecab3c8904bacb446c30a82148f11cc3d50f73fd75db34c44", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c858e2258c99ed0c3f3e3285c1f792c2b2e11c6bf1c410b30fc750b6862a5460", "generation_seconds_batch": 25.661776268971153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0229754447937012, "target_z": 1.523437507743315, "ce": 5.550024509429932, "genuineness": 4.519899368286133, "identity": 0.6044689416885376, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9b78e95664caf77ecab3c8904bacb446c30a82148f11cc3d50f73fd75db34c44.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "6a2113478daa98ab22e9a49fb58a62a0a6f3c653288f594bed079b36a2916e6f", "generation_seconds_batch": 17.860208133002743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.043044477701187134, "target_z": -0.2871093803773022, "ce": 6.292664527893066, "genuineness": 4.381826400756836, "identity": 0.8082945942878723, "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_Infatuation/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "heldout-es-2", "language": "es", "sentences": [ "La carretera gira a la izquierda tras el puente.", "Sigue... hasta la pequeña puerta de madera.", "Te esperaré al otro lado." ], "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-es-2", "key": "9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1833802ff1488bd54f2e62245a2a222711c76931c94ab8613c7e149835ae68f7", "generation_seconds_batch": 20.598119886941276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03670188784599304, "target_z": -0.2988281204830661, "ce": 6.109982967376709, "genuineness": 4.570107460021973, "identity": 0.6670445203781128, "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_Infatuation/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "9cf3e4d617bcf51d7f9d7a57f89f7350e3c625abe8f279049be3a47abd2947ea", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b675720a752dcbb01330d5eb0ad84155603902968eb74869e7ef67d651cb05b0", "generation_seconds_batch": 23.71452081494499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15562555193901062, "target_z": -0.07910155077748116, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.528321385383606, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9cf3e4d617bcf51d7f9d7a57f89f7350e3c625abe8f279049be3a47abd2947ea.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": "9cfda4cd5e3a7d70e77ba42f047d079a919f4ca8cea908c7b0b866ec499d1a07", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "f99612f8fc1d9a007013bbd438672ff555be852d2a64317f37c2e7ed3a8afc2c", "generation_seconds_batch": 19.411317800055258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15166142582893372, "target_z": -0.08642577710947728, "ce": 6.268836498260498, "genuineness": 4.074300289154053, "identity": 0.5425297021865845, "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_Infatuation/9cfda4cd5e3a7d70e77ba42f047d079a919f4ca8cea908c7b0b866ec499d1a07.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": "9d0a2622c81f06d9ce5fe86f2d1e061adec43710eed0308977c0b293dc1723d7", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8f5b9259bb9b7866208e3023f73821f39b12682cb54dce25b6ca7075a434a06d", "generation_seconds_batch": 33.189911843976006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6255061626434326, "target_z": 0.7890625404373127, "ce": 5.355429172515869, "genuineness": 4.243753433227539, "identity": 0.5891702175140381, "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_Infatuation/9d0a2622c81f06d9ce5fe86f2d1e061adec43710eed0308977c0b293dc1723d7.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": "9d0b793e2d11ffca278e7c04a6c251edbe19c9e6a9469fd475655d42c90d43a0", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f98f83974d317a83764a2a80ecbc4caa2d0cf7372a7b268561c1673333168dff", "generation_seconds_batch": 25.172945864964277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006046012043952942, "target_z": -0.35546874354723734, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.7431420087814331, "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_Infatuation/9d0b793e2d11ffca278e7c04a6c251edbe19c9e6a9469fd475655d42c90d43a0.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "9d148991709817e5da9ca122289174c0ce8057e9b2c2864f718b64293f172eb5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4aeb362eeebf0fe52309d3a494e92619c00685083a021edf351bdff81e738475", "generation_seconds_batch": 23.57725538604427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4457992911338806, "target_z": 0.4570312771016032, "ce": 5.246217727661133, "genuineness": 4.086852550506592, "identity": 0.4208037257194519, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando 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_Infatuation/9d148991709817e5da9ca122289174c0ce8057e9b2c2864f718b64293f172eb5.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "9d19f15308f5c052c3992bc248eb22331bec6943c92c83a7262de3505fcf799f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4c49bf5bb5afa62d3d463da4e0c8f4d9913e0f27a9dc91e42e9eec5b30f87e17", "generation_seconds_batch": 17.290859880042262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2904056906700134, "target_z": 0.1699218691925136, "ce": 5.530168056488037, "genuineness": 4.507347106933594, "identity": 0.44602054357528687, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9d19f15308f5c052c3992bc248eb22331bec6943c92c83a7262de3505fcf799f.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "9d4598e0dd4e69b4223d33a2d0e502c9784988d1dde1c2ce9b4af6da998a8c26", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e585ffed06971212bb2c1491d2e5d79c8214c5284cd969fa08aa1c3cc1fc74c1", "generation_seconds_batch": 24.815585158998147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07052905857563019, "target_z": -0.23632812736601297, "ce": 6.149696350097656, "genuineness": 4.419482707977295, "identity": 0.35465919971466064, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9d4598e0dd4e69b4223d33a2d0e502c9784988d1dde1c2ce9b4af6da998a8c26.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": "9e7360b7240e53e6670863c4e3a2002b41cf7bbd930ff722ef6c854c393bdc58", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a188e6620ebe637491f8c4ccd0a12238eb2d244d79ca95644c2da5c9016ebc7", "generation_seconds_batch": 23.74490503896959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 5.982900142669678, "genuineness": 4.432034492492676, "identity": 0.35529518127441406, "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_Infatuation/9e7360b7240e53e6670863c4e3a2002b41cf7bbd930ff722ef6c854c393bdc58.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "9e89bd641ec517634747f3baa13609a4c44f04a3a9e13a140192d629ec1b9020", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "381dc0b702582b2d63831e088b5b0cc3cad211b72536cb48f1d812e60b7521d9", "generation_seconds_batch": 23.26600405096542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3686310350894928, "target_z": 0.3144531256452763, "ce": 5.506340026855469, "genuineness": 4.319066047668457, "identity": 0.40580040216445923, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9e89bd641ec517634747f3baa13609a4c44f04a3a9e13a140192d629ec1b9020.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "9f60c529c7538f714d837dd0323ef92d847eef5ddee75621ab069ad8aebe42a2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d3b6f8b0f220281ee69f48fe2d0a49bbd2933630c07b0bd0693b44ddcbd876c", "generation_seconds_batch": 25.66079150198493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4627128839492798, "target_z": 0.48828128742602345, "ce": 5.609594821929932, "genuineness": 4.532451152801514, "identity": 0.2946449816226959, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9f60c529c7538f714d837dd0323ef92d847eef5ddee75621ab069ad8aebe42a2.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "9fc0bbee30a9f2e1d11b6eb6486facb358a1f8e5f577bf6613513ce4982a8887", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "58a92ae82745cc2d3024ba533650b53568657fc4b2a337b69388c3bcfe726ea4", "generation_seconds_batch": 26.155632229987532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32898980379104614, "target_z": 0.2412109173888897, "ce": 4.906171798706055, "genuineness": 4.20609712600708, "identity": 0.4018017053604126, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/9fc0bbee30a9f2e1d11b6eb6486facb358a1f8e5f577bf6613513ce4982a8887.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "a0526333cbc30a31d6c9f25e466580de147d944a6cdea64574887001c09a2598", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "594faa06b233170cd32a030ce57a56a6941b937306f369335e3f52dab4cede02", "generation_seconds_batch": 23.323735730024055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16328951716423035, "target_z": -0.0649414018943852, "ce": 6.213237762451172, "genuineness": 4.68307638168335, "identity": 0.6418917179107666, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a0526333cbc30a31d6c9f25e466580de147d944a6cdea64574887001c09a2598.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "a138586f7187d8b0dd88c94301eeb76eb4aa4ac7b2c1d1a7b98624d9b7347fa7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3c0d3e010733c334ef80be4125cca843bbf247228404077ebe8b722576bb9b84", "generation_seconds_batch": 19.329856134951115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01344570517539978, "target_z": -0.34179687091325034, "ce": 6.23706579208374, "genuineness": 4.570107460021973, "identity": 0.6894145607948303, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a138586f7187d8b0dd88c94301eeb76eb4aa4ac7b2c1d1a7b98624d9b7347fa7.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "a15f4b26ccf1125911f2a277e8ded416b0921293eeeccc365ce5a163777025e4", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bfd8ae8a7cb25ca21fcc9a89654210913c8df125137c71f37025fb0ea48c96f5", "generation_seconds_batch": 17.564126571058296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.043044477701187134, "target_z": -0.2871093803773022, "ce": 6.1894097328186035, "genuineness": 4.645420074462891, "identity": 0.6994562149047852, "hypothesis": "He encontrado la cajita. Estaba junto la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a15f4b26ccf1125911f2a277e8ded416b0921293eeeccc365ce5a163777025e4.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": "a17531ac1e5c0c5013a4b6e660d04588e84680bd2eb59613c428695f3dd383fd", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "d92bbabdd4e08382d728beb08f77b0d85c333f22e4317dc91afa59f76c595df5", "generation_seconds_batch": 18.434974618954584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.5955321192741394, "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_Infatuation/a17531ac1e5c0c5013a4b6e660d04588e84680bd2eb59613c428695f3dd383fd.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "a2ecdd983310e68da9fa343d37849fbd023c977b9051a153a601a0f602930d34", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3536fc48a03c69dbe15d092090e2eb17608aeeab55cf5577f74e92d6dbbf78ba", "generation_seconds_batch": 17.748936638003215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36757391691207886, "target_z": 0.31249996558526577, "ce": 6.054384231567383, "genuineness": 4.532451152801514, "identity": 0.7290562391281128, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a2ecdd983310e68da9fa343d37849fbd023c977b9051a153a601a0f602930d34.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "a2f02693bf0b4d516432f1ffecd49eb32abe7f43a8a3190f2109fcd0c9429113", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2de4282177180783091b6e6750be7473f66014f57b8ff72692c8e76f0ab7ce6b", "generation_seconds_batch": 24.192611722042784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5303671956062317, "target_z": 0.613281218596555, "ce": 5.7684478759765625, "genuineness": 3.8295347690582275, "identity": 0.31831300258636475, "hypothesis": "The 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_Infatuation/a2f02693bf0b4d516432f1ffecd49eb32abe7f43a8a3190f2109fcd0c9429113.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "a37eea3da36a5e4d6311ea09a2b106eff6b500b3522735f86aff856aff43a300", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "be0098ce9dbd20f2ef92235954e3a3d147ee962adf4347eca6a3a06168a08653", "generation_seconds_batch": 23.626117254025303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 6.308549880981445, "genuineness": 4.143336772918701, "identity": 0.32674095034599304, "hypothesis": "The 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_Infatuation/a37eea3da36a5e4d6311ea09a2b106eff6b500b3522735f86aff856aff43a300.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "a3de20815e24fa1f73013843a96a3f24b55408f6d81f6945d791d0bfc356372d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4b54c46dc7f866ec53db01ddde0bb4ecc52c983a0f48dc9ee79aaf2dd82672f2", "generation_seconds_batch": 25.66079150198493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49442583322525024, "target_z": 0.546874987954843, "ce": 5.764476776123047, "genuineness": 4.532451152801514, "identity": 0.42991670966148376, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a3de20815e24fa1f73013843a96a3f24b55408f6d81f6945d791d0bfc356372d.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": "a40f5ffc710f03d0cc350ba3b0167a9d7a45776554e538f114d2e7cabef20b70", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f4257b39b824931a94b81eb1c4262baa7f2f934e7d79f482134e48b3dc7c5e2", "generation_seconds_batch": 17.705739979050122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621577262878418, "target_z": -0.28125001032442026, "ce": 5.681078910827637, "genuineness": 4.532451152801514, "identity": 0.4594801366329193, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter. Bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a40f5ffc710f03d0cc350ba3b0167a9d7a45776554e538f114d2e7cabef20b70.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "a4277c8b093de5892b2434f6ce7d6a2a26e960603a8874096e9d72881f4bd35e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "10722e9773dda26a8873f04dd06330d1276b66b825eb3184f75f529dc82f00f6", "generation_seconds_batch": 25.687962163006887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006046012043952942, "target_z": -0.35546874354723734, "ce": 6.165581703186035, "genuineness": 4.6203155517578125, "identity": 0.6769847869873047, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a4277c8b093de5892b2434f6ce7d6a2a26e960603a8874096e9d72881f4bd35e.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": "a438886c8b2e3e0304d994407fb6d1751dde055bcac3ac0db9c1225d52745910", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "956b33c8dae485fc9ff6a903194f3a495cd0b9752be5f80da21257035ea9cdb9", "generation_seconds_batch": 25.216837968910113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.5809063911437988, "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_Infatuation/a438886c8b2e3e0304d994407fb6d1751dde055bcac3ac0db9c1225d52745910.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "a4ada683ccc51f39a20143d54b99a80209827f7e9a490f8853f989bc11dd629a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d6e7fee9612fafd40cb65be642d64fa5507e30dd7486f788d14d3ed1a9386739", "generation_seconds_batch": 30.074936847086065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17888173460960388, "target_z": -0.036132800347296976, "ce": 6.435632705688477, "genuineness": 4.444586753845215, "identity": 0.35451406240463257, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a4ada683ccc51f39a20143d54b99a80209827f7e9a490f8853f989bc11dd629a.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "a4fea8149af73e0b9508951a8dbe81fd15107cb49dc7c4369cee7a9664a29147", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2fdbd4b2dcc5c964c7733488909e6b46a4022d9749ff2671b675f194f13e11cf", "generation_seconds_batch": 23.384911539964378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.99760502576828, "target_z": 1.47656243719311, "ce": 5.605623245239258, "genuineness": 4.545003414154053, "identity": 0.7962702512741089, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a4fea8149af73e0b9508951a8dbe81fd15107cb49dc7c4369cee7a9664a29147.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "a538cd32fbfaf59631fd37297bc0129031e52028cb84dc13746ad727ee22d6df", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b5494d46fafa6f7576f815f749593984529bf721f056189cab58efc2a39edf8", "generation_seconds_batch": 18.270366001990624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2946341037750244, "target_z": 0.17773439930540605, "ce": 6.006728172302246, "genuineness": 4.7081804275512695, "identity": 0.7225607633590698, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a538cd32fbfaf59631fd37297bc0129031e52028cb84dc13746ad727ee22d6df.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "a59306ae90b1b60b70667599ae3886d2504daded1a2d9b66695742553b722caa", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c67c82791697629ccf093c829e9ed15c7b0600efaae57138eafc98a7dd7271c", "generation_seconds_batch": 18.78566689498257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05890096724033356, "target_z": -0.25781250258110505, "ce": 5.262103080749512, "genuineness": 4.243753433227539, "identity": 0.3056771457195282, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a59306ae90b1b60b70667599ae3886d2504daded1a2d9b66695742553b722caa.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "a646373206910de4c3648afd9d79df71e8c09e8b1cd964ce9e4ad0f65c7fc435", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f91286723e15e16067549da71ae03ed65e084206ae5672143fc7611141139462", "generation_seconds_batch": 24.247461585095152, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1640823483467102, "target_z": -0.06347654561527102, "ce": 5.974957466125488, "genuineness": 4.425758361816406, "identity": 0.49700722098350525, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a646373206910de4c3648afd9d79df71e8c09e8b1cd964ce9e4ad0f65c7fc435.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "a64842a5a83de69eb2f103880229db2221d19da7edb9609ad068c2e51c4cda2b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6d9d8591b34c6eb16981919cbec2749529f12c85bb5f56e88b82480461190313", "generation_seconds_batch": 21.768069805926643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17941027879714966, "target_z": -0.035156247849079114, "ce": 6.078212261199951, "genuineness": 4.65797233581543, "identity": 0.5713669061660767, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a64842a5a83de69eb2f103880229db2221d19da7edb9609ad068c2e51c4cda2b.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "a6960b1eb73717ccb7e417091cba31a075f172e88d4f569dc8a6a7b409c191ee", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4f3413c340e1d7a09231dbc2966a1dddf38098293be7dd3b7baa2f42c1391197", "generation_seconds_batch": 26.02610400202684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0927281454205513, "target_z": -0.19531249569815823, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.4671367406845093, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a6960b1eb73717ccb7e417091cba31a075f172e88d4f569dc8a6a7b409c191ee.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "a69f3569e1d76af62f2eef3ed58d82f4ff8dd6df20bd4e2d0d9238d4c4f9e365", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d9b25f94ab8a1689a5cc74b21c7ebf24b9edc7f1d1feed6a1d0c8fceaa2181cc", "generation_seconds_batch": 17.87093402899336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4140862822532654, "target_z": 0.39843746644563416, "ce": 6.086154937744141, "genuineness": 4.193545341491699, "identity": 0.2354002445936203, "hypothesis": "The 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_Infatuation/a69f3569e1d76af62f2eef3ed58d82f4ff8dd6df20bd4e2d0d9238d4c4f9e365.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": "a6d61c9ab4bdb25e111f6ec09051911406c39d033a8b8895698d5506c9bde98e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "359f842564a81486aa637bf4a31994ed311c420e59bff30f4abd37775525e0c7", "generation_seconds_batch": 24.04342711006757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05890096724033356, "target_z": -0.25781250258110505, "ce": 5.998785495758057, "genuineness": 4.507347106933594, "identity": 0.46718770265579224, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a6d61c9ab4bdb25e111f6ec09051911406c39d033a8b8895698d5506c9bde98e.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "a73b84de55312f0c87b6380f33c17dc71b017c91ccc55b9450b09ded4d6caa52", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1eabccb00d2fc5750d5276472f8f77cc3d1603b6c6c3186154d74d1deca1bb55", "generation_seconds_batch": 28.562153213075362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06894341111183167, "target_z": -0.23925781239245394, "ce": 6.117925643920898, "genuineness": 4.6956281661987305, "identity": 0.3194063901901245, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a73b84de55312f0c87b6380f33c17dc71b017c91ccc55b9450b09ded4d6caa52.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "a823e166bb15d280cfe806e3fde69c79d80b7ed3e49ca641b6a35fe59f6036fc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ec5a214b9e01788b6a9ff3c15f2891b15ddc24e40264835a87f1037169b9d64e", "generation_seconds_batch": 26.019405515980907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09167104214429855, "target_z": -0.19726562822638133, "ce": 5.700935363769531, "genuineness": 4.7458367347717285, "identity": 0.8410259485244751, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a823e166bb15d280cfe806e3fde69c79d80b7ed3e49ca641b6a35fe59f6036fc.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "a87a57de42eeb227dfce86d3656f185b0a4e8a8272682da3c3d9e14608bbcff5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "831c287b6b1063b67c6586117b57324addc6c7142637aa3ae45a8d947d5315ee", "generation_seconds_batch": 25.928880390012637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018731191754341125, "target_z": -0.33203126333570954, "ce": 6.260893821716309, "genuineness": 4.557555198669434, "identity": 0.7460371255874634, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a87a57de42eeb227dfce86d3656f185b0a4e8a8272682da3c3d9e14608bbcff5.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": "a891c3fde70fe68f9c8287a67401d6b4bc06c27a430d6e25263794db2f4faacb", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "837b168baeb9717f3d4a5851b88abe2082fa7b9359b50a21e6150f786a9814b2", "generation_seconds_batch": 18.38524438405875, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08110005408525467, "target_z": -0.2167968709132503, "ce": 5.967014789581299, "genuineness": 4.570107460021973, "identity": 0.43763402104377747, "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_Infatuation/a891c3fde70fe68f9c8287a67401d6b4bc06c27a430d6e25263794db2f4faacb.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": "a89967fcbc7559217fad1566766b86f2b22d6d94acb432275fb3d3392b144bb4", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f702bab610cf8190f2e4671a73a343af66d6e563d04c1a27ed454f715b9db4fc", "generation_seconds_batch": 18.042604333953932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15245425701141357, "target_z": -0.0849609208303631, "ce": 5.863759994506836, "genuineness": 4.632867813110352, "identity": 0.6835824251174927, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a89967fcbc7559217fad1566766b86f2b22d6d94acb432275fb3d3392b144bb4.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "a118410ed4062708081b3873a0cb1286bb1a1598d4746be6384b4bd6b32cd1ac", "generation_seconds_batch": 17.482693555997685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006046012043952942, "target_z": -0.35546874354723734, "ce": 6.1894097328186035, "genuineness": 4.375550270080566, "identity": 0.7662980556488037, "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_Infatuation/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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "49731caf729cdb8adba071c1633b332e6ecd57ce100e61fc500b7c7c43efab71", "generation_seconds_batch": 16.938520982977934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01344570517539978, "target_z": -0.34179687091325034, "ce": 6.260893821716309, "genuineness": 4.607763767242432, "identity": 0.7263253331184387, "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_Infatuation/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "a97e3bcfb3121f821a0ab18b90b49614c4cda1193457d654a6ca7e11d965c8a1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e7b26d91c6cb385bafa14e550843046d712eb949ce7c3f7937f249511bb35a9f", "generation_seconds_batch": 18.932285959017463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3823733329772949, "target_z": 0.3398437659168146, "ce": 5.847874641418457, "genuineness": 3.7667744159698486, "identity": 0.1077030748128891, "hypothesis": "The 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_Infatuation/a97e3bcfb3121f821a0ab18b90b49614c4cda1193457d654a6ca7e11d965c8a1.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "a9d34ae0703b7cf71b9c1c6227099a68a48cd893e9f985e202addad9f5f138f2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "076e7d9788505185227140088cbf7142a81fd0d775b4948b885cc151e718681d", "generation_seconds_batch": 25.812623452045955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07581455260515213, "target_z": -0.2265625060225785, "ce": 6.054384231567383, "genuineness": 4.507347106933594, "identity": 0.5932039022445679, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a9d34ae0703b7cf71b9c1c6227099a68a48cd893e9f985e202addad9f5f138f2.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": "a9e2a77e761a52b801dd9afa4e3df3881e604f443f6be733086f1255bf3c9d94", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "4f9615fef83c1b3eaacebf8af63b37c1efddf8ec80fa8de6ab19506230e01537", "generation_seconds_batch": 19.97744996799156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11439867317676544, "target_z": -0.1552734440603087, "ce": 6.229123115539551, "genuineness": 4.6705241203308105, "identity": 0.529799222946167, "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_Infatuation/a9e2a77e761a52b801dd9afa4e3df3881e604f443f6be733086f1255bf3c9d94.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "a9f6cad0f834d35e2a407dc41827f68bd9fe855272248bcfd39310a80c83b5a4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c65f54bc66b14044522fb98e151ae3e062b439aae6efa7b8c3db261ea91e5969", "generation_seconds_batch": 17.613793781027198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 6.165581703186035, "genuineness": 4.758388519287109, "identity": 0.736187219619751, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/a9f6cad0f834d35e2a407dc41827f68bd9fe855272248bcfd39310a80c83b5a4.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "aa1740961ba26004765c566718ddc36d6509edff6ee9ec56e4347c4f1f5da517", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "380ca64659f5d0456310f923e55e27d461570a24b3138baa1742956081eb6611", "generation_seconds_batch": 23.22913279396016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24257194995880127, "target_z": 0.08154295955481321, "ce": 5.95112943649292, "genuineness": 4.7332844734191895, "identity": 0.8354402780532837, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/aa1740961ba26004765c566718ddc36d6509edff6ee9ec56e4347c4f1f5da517.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "aa3dd07a25081f05d44f37ad8c17ae44ce623cd894aeee79d08a00e887da8394", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f9057c329435dd9e511df7e4074180ea59a9574c551f48e41a2ae37c4a8eb9d5", "generation_seconds_batch": 23.066003697924316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.471169650554657, "target_z": 0.5039062375246588, "ce": 6.022613525390625, "genuineness": 4.570107460021973, "identity": 0.7100709676742554, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/aa3dd07a25081f05d44f37ad8c17ae44ce623cd894aeee79d08a00e887da8394.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "aa3eb4fa949698567c8fa09c982899bb9bce9972d1740406b67c7f45ee83293f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a6d7a5a9ac152dd8c144d4dfbf9884ba18c7a8ac79b5deace8f41770d71927a3", "generation_seconds_batch": 24.474192184978165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35171744227409363, "target_z": 0.283203115320856, "ce": 5.569881439208984, "genuineness": 4.457139015197754, "identity": 0.44427746534347534, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/aa3eb4fa949698567c8fa09c982899bb9bce9972d1740406b67c7f45ee83293f.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "aa7a91d40386f68fd64b5ab4346f48cc6f52c876efc3644813458720a21873d0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28e24440e8e8ba9600a8998feccd3cc961e6ece98bd523073b7f19043cfc5c87", "generation_seconds_batch": 23.95335117506329, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059958070516586304, "target_z": -0.25585937005288195, "ce": 5.736677646636963, "genuineness": 4.432034492492676, "identity": 0.45908236503601074, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/aa7a91d40386f68fd64b5ab4346f48cc6f52c876efc3644813458720a21873d0.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "aadf225225f2bcb63d60fbbf1346875551e8bd0f2e7079c58f7d497e8bc9186a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ed9efcb4632f65c7b6b2e85155a286d8d50157fb9fb9e5170856f22ec6a9adb", "generation_seconds_batch": 24.258002404938452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06101517379283905, "target_z": -0.25390623752465885, "ce": 5.649308204650879, "genuineness": 4.482243061065674, "identity": 0.6401464343070984, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/aadf225225f2bcb63d60fbbf1346875551e8bd0f2e7079c58f7d497e8bc9186a.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "aae4e1bfb9916c985bc2ceae72fa7ae87330c202976bf36c88ee8d6f2636ec68", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "523d3f671e06404c009ff297a9d1cdd4d7577b47bf990e26e56017c580e55cb6", "generation_seconds_batch": 24.62782061996404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5705369710922241, "target_z": 0.6874999793511595, "ce": 5.8875885009765625, "genuineness": 4.7834930419921875, "identity": 0.9222866892814636, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/aae4e1bfb9916c985bc2ceae72fa7ae87330c202976bf36c88ee8d6f2636ec68.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97dbfeeb5390917a3bb7d3ef6d50f9c3e4620be63f9e66ade87410d3e57ccc02", "generation_seconds_batch": 17.124287017970346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1291980743408203, "target_z": -0.1279296712605473, "ce": 6.499174118041992, "genuineness": 4.168440818786621, "identity": 0.4208165407180786, "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_Infatuation/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.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": "abd5648414ee4866e2ef7f1be18e7b464bfa2c597d07b7d1ff0fecbc7c899564", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8bee69b6f7858f22f72d6b15dfd1414eba2d973d1e172ec394f6d7d2e073c400", "generation_seconds_batch": 18.321385471965186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6212777495384216, "target_z": 0.7812500103244203, "ce": 5.816103935241699, "genuineness": 4.7332844734191895, "identity": 0.5115993022918701, "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_Infatuation/abd5648414ee4866e2ef7f1be18e7b464bfa2c597d07b7d1ff0fecbc7c899564.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "ac00e4e7da4ab62616be34bcde923fe808f886375b99466bd5a7b2e83a9d2265", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c1ee58a0e1106bfc5146d4474a628fb3762e136d409a0888cb79154fbab70657", "generation_seconds_batch": 18.07707437092904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3094334900379181, "target_z": 0.20507814457338008, "ce": 5.9431867599487305, "genuineness": 4.356721878051758, "identity": 0.7905570268630981, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ac00e4e7da4ab62616be34bcde923fe808f886375b99466bd5a7b2e83a9d2265.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "ac4d3e08d44d2ddf17195fd029173bf7fec752e8ea9de51ae1467bfbdf22fc3c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5595263eb7cf15bf29066309c0be1bf4f4d70e2cfeb5ab99bb33f850eefeecee", "generation_seconds_batch": 18.72399408998899, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6318487524986267, "target_z": 0.8007812805430766, "ce": 5.784333229064941, "genuineness": 4.846253395080566, "identity": 0.7325708866119385, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ac4d3e08d44d2ddf17195fd029173bf7fec752e8ea9de51ae1467bfbdf22fc3c.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "ac6fe1ea3a42985d10f95b963fa554cdcc633571a91789471dca50013e93049e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "648f68bea55fab305b2fc5a612415a0f8b3677e394c3685e8e4de6045b7fa473", "generation_seconds_batch": 23.387921464047395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0013536810874938965, "target_z": -0.36914061618122435, "ce": 6.133810997009277, "genuineness": 4.607763767242432, "identity": 0.726611852645874, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ac6fe1ea3a42985d10f95b963fa554cdcc633571a91789471dca50013e93049e.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": "acb75b6d09704452480e9ac14df40a1b19c68edd9a5384549bfd82fa3a337a6e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28aa607c04562ffc1e024873785dd3a9601e2ea2fd72c19ed4762cab7ec53a4b", "generation_seconds_batch": 23.363003949983977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04515868425369263, "target_z": -0.283203115320856, "ce": 5.764476776123047, "genuineness": 4.545003414154053, "identity": 0.6222602128982544, "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_Infatuation/acb75b6d09704452480e9ac14df40a1b19c68edd9a5384549bfd82fa3a337a6e.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "ad52c4eda4ebb83d9c8a2a3e949e2bb440603dbe8593c57ac18da1808ef7087a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9f86eb8c97bdc57711a5e30b8a811b7d71b608ec766e5991f91d428c21c3d47f", "generation_seconds_batch": 26.016467956011184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8834383487701416, "target_z": 1.2656250051622102, "ce": 5.08339262008667, "genuineness": 4.331617832183838, "identity": 0.5132440328598022, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuando estás lista.", "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_Infatuation/ad52c4eda4ebb83d9c8a2a3e949e2bb440603dbe8593c57ac18da1808ef7087a.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "48f3ab127a8bdb1fa5d2f18fe48536f764553feb63373a013c56e9249ac90fa4", "generation_seconds_batch": 17.60671513399575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014038875699043274, "target_z": -0.39257812392453956, "ce": 6.157639026641846, "genuineness": 4.2249250411987305, "identity": 0.4414396286010742, "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_Infatuation/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "de36dc88ab8cf252be0b4e808d76113c686dc170e16cab7e30264e9869a1d1fe", "generation_seconds_batch": 19.305998158990405, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022959589958190918, "target_z": -0.32421876075460443, "ce": 6.443574905395508, "genuineness": 4.18726921081543, "identity": 0.3560013771057129, "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_Infatuation/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "ae90728b2e68bc6ff4dcb9c31136a9e3424e36456fdccf14a05eb6e9a196e5e0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "626d4bafb3aafd97122e62e6cfed128b852c84b69b1384ac663fe5f84393f859", "generation_seconds_batch": 23.33234053198248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11387012898921967, "target_z": -0.1562499965585266, "ce": 6.205295085906982, "genuineness": 4.68307638168335, "identity": 0.46229004859924316, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ae90728b2e68bc6ff4dcb9c31136a9e3424e36456fdccf14a05eb6e9a196e5e0.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "aecedbdb4a7f48434c8749a979c2b2c558056a8c34addb22a2dcd7f03ffdefb0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fc6cc36aac0322ad99fca32c96cc0e5747107305721281e18a9e5ff32030b6b", "generation_seconds_batch": 22.83906665293034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017674103379249573, "target_z": -0.33398436833214523, "ce": 6.157639026641846, "genuineness": 4.337893962860107, "identity": 0.5206056833267212, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/aecedbdb4a7f48434c8749a979c2b2c558056a8c34addb22a2dcd7f03ffdefb0.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "aedc12dc25d35a923b6d119108edd238ec75390a9759b6a28ac70305c9a70003", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d48f95871291fe1ed8489f885d1e46b9d479a589e53187a096b6031f307067d9", "generation_seconds_batch": 22.88149489206262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7946419715881348, "target_z": 1.1015624234272163, "ce": 5.6254801750183105, "genuineness": 4.030367851257324, "identity": 0.3161318898200989, "hypothesis": "The 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_Infatuation/aedc12dc25d35a923b6d119108edd238ec75390a9759b6a28ac70305c9a70003.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "af14dca2cf6cff0d6e8d3f85770485648609f8440607a7da9f2ca121f515244d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "680df2f90b7e03f8c9fc4a0201bfb308077292d602df5272b93e1aba17cff9ab", "generation_seconds_batch": 23.378950819023885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3057336211204529, "target_z": 0.1982421669587055, "ce": 5.561938762664795, "genuineness": 4.545003414154053, "identity": 0.6908288598060608, "hypothesis": "J'ai trouvé la 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_Infatuation/af14dca2cf6cff0d6e8d3f85770485648609f8440607a7da9f2ca121f515244d.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "af6bbca68239ac109607bea75326fb3248465504a47a5c82dacc69e66c3c3b07", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cf3fc39f61f2cce249100fc0fa8d2e30652b10823fe6383faa76e592ae16ecc2", "generation_seconds_batch": 26.827364495955408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15906111896038055, "target_z": -0.07275390447549027, "ce": 5.903473377227783, "genuineness": 4.532451152801514, "identity": 0.5894676446914673, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/af6bbca68239ac109607bea75326fb3248465504a47a5c82dacc69e66c3c3b07.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "af783014314357f6cffbaea9da6c58610e33556d563cd1c2d3916774c32fd973", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f737849c9c56493f7e6988369820e7e69eed71715d851a6a3d8ecabace04bc0e", "generation_seconds_batch": 23.26600405096542, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24917882680892944, "target_z": 0.09375000344147343, "ce": 5.34748649597168, "genuineness": 4.356721878051758, "identity": 0.4813585877418518, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/af783014314357f6cffbaea9da6c58610e33556d563cd1c2d3916774c32fd973.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "af9a2898d47df0e12f4975137db808474fca089ce7b8835cf35e8d5b78872a74", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5f70874cefdaaa4523bb875d69ced995864e6313eafa064f653431cdf40c8774", "generation_seconds_batch": 23.376298847957514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07792875170707703, "target_z": -0.22265625473202597, "ce": 6.09409761428833, "genuineness": 4.758388519287109, "identity": 0.5270598530769348, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/af9a2898d47df0e12f4975137db808474fca089ce7b8835cf35e8d5b78872a74.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "afc556a6fbfb032cba0faa101d442094cbb24e94a10ba0b9bbefc265f9669797", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "93ff80c19e91c176c72b1a3b30dfd7d574296e100ddc7053fc92df8a3a544d18", "generation_seconds_batch": 24.606894865981303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18476183712482452, "target_z": -0.025268564326314233, "ce": 6.308549880981445, "genuineness": 4.469690799713135, "identity": 0.4759524464607239, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/afc556a6fbfb032cba0faa101d442094cbb24e94a10ba0b9bbefc265f9669797.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "afdc9dd19a0dae2f821e76c48805bd6a4dc330cdb3c6a1f42c531f87256d411f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba92e20e67c6301418db0a3327eead6489d76d4d4576db07c8ce5e46171435f9", "generation_seconds_batch": 23.182461167918518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04832997918128967, "target_z": -0.27734374526797406, "ce": 6.284721851348877, "genuineness": 4.632867813110352, "identity": 0.5611306428909302, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/afdc9dd19a0dae2f821e76c48805bd6a4dc330cdb3c6a1f42c531f87256d411f.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "afdfb34e140accaafd06693d030d973fd274bd0814d6ea362884ff27abec682b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "52cbdb9a14c4ddb916d2e4bc356d2e0fa73d5d3a7106a62d2ff890d514aaf15e", "generation_seconds_batch": 26.08297708106693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11069882661104202, "target_z": -0.16210938037730221, "ce": 6.181467056274414, "genuineness": 4.808597087860107, "identity": 0.8061652183532715, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/afdfb34e140accaafd06693d030d973fd274bd0814d6ea362884ff27abec682b.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "b03774d860e249b8616c2de5549746f6248201933e128317cb596f739bc5f341", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c92ab6f10f2d84580e5cb26f56f61b6b1039b770815536ef2c074f4526c36a45", "generation_seconds_batch": 23.108276992919855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04832997918128967, "target_z": -0.27734374526797406, "ce": 6.221180438995361, "genuineness": 4.883909225463867, "identity": 0.7465296983718872, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b03774d860e249b8616c2de5549746f6248201933e128317cb596f739bc5f341.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "b0b6fc15ff74729496c3335f83ddcbaeb7baa1c07faa65435f7f43ca6329609f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "29a83ac50e9eb0db8e5f1fe9f45b6954984895e2464a4c2b16a81c31d3ed0748", "generation_seconds_batch": 23.57725538604427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5367097854614258, "target_z": 0.624999958702319, "ce": 5.033751010894775, "genuineness": 3.9425034523010254, "identity": 0.3801306486129761, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b0b6fc15ff74729496c3335f83ddcbaeb7baa1c07faa65435f7f43ca6329609f.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "b0d8dde3b513d9350f3a8073fc950dda17442a8497f871668dab842b149b2e15", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3f302086edc4fa33817675e8d656313332436bad3b45e5a3420eda460d5564b", "generation_seconds_batch": 28.93170859501697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008753374218940735, "target_z": -0.3828124888152114, "ce": 5.959072113037109, "genuineness": 4.532451152801514, "identity": 0.5910505056381226, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b0d8dde3b513d9350f3a8073fc950dda17442a8497f871668dab842b149b2e15.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "b138660451292752ea2974d7c79c57dc55bec98ebb87c46fba27d3dbb555bba3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bca586beaeb51ec775e06f0021c82c8697ba6e6a95e4132eec14483c6d5ee9b5", "generation_seconds_batch": 32.48294028406963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1624966859817505, "target_z": -0.06640625817349938, "ce": 5.609594821929932, "genuineness": 4.256305694580078, "identity": 0.6062673330307007, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b138660451292752ea2974d7c79c57dc55bec98ebb87c46fba27d3dbb555bba3.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "b146d76a5251cf0a622deea764fac6cdec66e2812ca2554888be4b989c7448d3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0f4394adc0a086f76f68b461ecacd06453ce1dfb982a2ab9191ea9b814d07f2e", "generation_seconds_batch": 22.47107587393839, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 5.7128496170043945, "genuineness": 4.457139015197754, "identity": 0.5019311308860779, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b146d76a5251cf0a622deea764fac6cdec66e2812ca2554888be4b989c7448d3.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "b172aee1a95389cbe39668c0d9ed6f250e74f2755c986bccd5ed3f08513f818c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3d4542fecf136dc00e740df7e83f7c907e5f8b4b9e7a4e2f25299248b8c178a1", "generation_seconds_batch": 18.934529917081818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06894341111183167, "target_z": -0.23925781239245394, "ce": 6.149696350097656, "genuineness": 4.7081804275512695, "identity": 0.8087198734283447, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b172aee1a95389cbe39668c0d9ed6f250e74f2755c986bccd5ed3f08513f818c.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "b1dad94cdddc3611f719a6aae21114a7ab82c6ea4ac62080c67686baa7103b15", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4d7f2e7b52b9a508645e8703020d54f1c30f51757d95e8ecd27990c77bab9d9", "generation_seconds_batch": 24.378000757074915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3686310350894928, "target_z": 0.3144531256452763, "ce": 4.995030403137207, "genuineness": 4.243753433227539, "identity": 0.34601718187332153, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b1dad94cdddc3611f719a6aae21114a7ab82c6ea4ac62080c67686baa7103b15.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "b2241676c5ce8e232d4fbebbc08536af877a90e7d37c757b84840ad5e7d4cc61", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "732ad05d454439cee79d0e2810c486d2af69395c053b480a6aa78afb0c5cba77", "generation_seconds_batch": 24.828052781056613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2375507354736328, "target_z": 0.07226562822638133, "ce": 6.0146708488464355, "genuineness": 4.300237655639648, "identity": 0.6779520511627197, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b2241676c5ce8e232d4fbebbc08536af877a90e7d37c757b84840ad5e7d4cc61.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "b2cee71a2b7c34d85a84f049a0a46aec2d9be7f725463715c1846f018055d95a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "633bcaa9b2e7982f3bfb481001b608512dd591e7cabbb639eeef0bc9ac6fa134", "generation_seconds_batch": 23.340271739056334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5367097854614258, "target_z": 0.624999958702319, "ce": 5.657250881195068, "genuineness": 4.281409740447998, "identity": 0.2793085277080536, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b2cee71a2b7c34d85a84f049a0a46aec2d9be7f725463715c1846f018055d95a.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "b377949148789b140880ff4247194dcadc07043a7190cd64a53fcca4cad127c3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0bc669a4b3dcfe080327dee113b67f9afd7135e93c732b235134c430a90c620b", "generation_seconds_batch": 25.26687449403107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04515868425369263, "target_z": -0.283203115320856, "ce": 5.804190158843994, "genuineness": 4.582659721374512, "identity": 0.6307907104492188, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b377949148789b140880ff4247194dcadc07043a7190cd64a53fcca4cad127c3.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "b37aff6e8a4db15fc457901fe533b79d3a7ada41b9c1c66a26de40722f816791", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "869cb05a80d0a8c203eff33c84619885317b9bbe135a741df590fc4d5b0ad359", "generation_seconds_batch": 23.71982024004683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1318408101797104, "target_z": -0.12304688123767057, "ce": 6.125868320465088, "genuineness": 4.218649387359619, "identity": 0.4278538227081299, "hypothesis": "The 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_Infatuation/b37aff6e8a4db15fc457901fe533b79d3a7ada41b9c1c66a26de40722f816791.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "b3feeef1a5bc906e394255c1d2a06e926977c4bfbc119e421a72435e922601b4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "679c2abe7db99905e0d03e375f9c7a4b6a41813da142ddc25cd15831cea7baeb", "generation_seconds_batch": 22.838002366013825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8665247559547424, "target_z": 1.2343749948377898, "ce": 5.847874641418457, "genuineness": 4.406930446624756, "identity": 0.3034435510635376, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b3feeef1a5bc906e394255c1d2a06e926977c4bfbc119e421a72435e922601b4.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "b4044cd68a63391848b674de060cb39c6e5af1a7eb7b6948dcda839bdf4a1980", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7a859b297968a0b1574bdd229e483a33952025b5b9687df5d7cada5c57b3e3a7", "generation_seconds_batch": 26.065680474042892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003931805491447449, "target_z": -0.35937500860368354, "ce": 5.534139156341553, "genuineness": 4.218649387359619, "identity": 0.5201707482337952, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b4044cd68a63391848b674de060cb39c6e5af1a7eb7b6948dcda839bdf4a1980.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "9438461a6360ce5b835246cf862f77b0d62f54fcf5c2f13199d6017b4c274979", "generation_seconds_batch": 18.881001493078656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030359283089637756, "target_z": -0.3105468881206174, "ce": 6.340320587158203, "genuineness": 4.21237325668335, "identity": 0.575303316116333, "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_Infatuation/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.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": "b47547cb343c07dd9efac405c6a50c62010f0f8b62c5cb1ad46c69079652b1bb", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "dc67310b6f2acfbba287f18697ae83cf22deefd9cab3dfa83988946b29b92c8f", "generation_seconds_batch": 18.022460600011982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2930484414100647, "target_z": 0.1748046867471777, "ce": 5.816103935241699, "genuineness": 4.595211505889893, "identity": 0.6712877154350281, "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_Infatuation/b47547cb343c07dd9efac405c6a50c62010f0f8b62c5cb1ad46c69079652b1bb.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "b5073af7a85254292f685a47425c4c339f99761a7cd02ba2693c76bd98eba2af", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "00db9d6de18ab54423148694c2dc2fd59e40d918f98bfb8a24a31daf4ee07220", "generation_seconds_batch": 25.660001867916435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13818341493606567, "target_z": -0.1113281136001193, "ce": 5.935244083404541, "genuineness": 4.482243061065674, "identity": 0.43277812004089355, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b5073af7a85254292f685a47425c4c339f99761a7cd02ba2693c76bd98eba2af.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "b50bb6d4f7d401f3c066bec84afdd32ca560472b215bbe6f768cffda7359d3c6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "eb4f7476f280a1ebf5d493f0773915e636f722ac050de9ed0f0a67b07e9575c7", "generation_seconds_batch": 23.304559946991503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02084539830684662, "target_z": -0.3281249982792633, "ce": 6.0146708488464355, "genuineness": 4.645420074462891, "identity": 0.7360388040542603, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b50bb6d4f7d401f3c066bec84afdd32ca560472b215bbe6f768cffda7359d3c6.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "b5b21a7580a185a551b2046fc75423eff61f8e40af24b0319baede0d5c0ad516", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "211a2c6c5521b2856a34f6bb0309df069959428919b1e1873351463b2526161c", "generation_seconds_batch": 18.04726831498556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01344570517539978, "target_z": -0.34179687091325034, "ce": 6.316492557525635, "genuineness": 4.6705241203308105, "identity": 0.6921891570091248, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b5b21a7580a185a551b2046fc75423eff61f8e40af24b0319baede0d5c0ad516.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": "b636c32e9dc463a77976dae20fa8643bbd327230f744304f41b47533daa20a2c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "ed827491c2aae1f936244ac0a7bf5dbbff9b25462b12306ddad0d983c8f57931", "generation_seconds_batch": 20.030469563091174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06101517379283905, "target_z": -0.25390623752465885, "ce": 5.919358730316162, "genuineness": 4.582659721374512, "identity": 0.40876293182373047, "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_Infatuation/b636c32e9dc463a77976dae20fa8643bbd327230f744304f41b47533daa20a2c.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "b65c0a8a0a86d7d64100c4bfbe3354068bf890b50ee600b56eb02c3a2a1f1913", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "59c27936aef32e5438d8d7fa3299508246acc256614ad836c22bcfebab778102", "generation_seconds_batch": 23.298536350019276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12391257286071777, "target_z": -0.13769530636987548, "ce": 6.340320587158203, "genuineness": 4.519899368286133, "identity": 0.5150966048240662, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b65c0a8a0a86d7d64100c4bfbe3354068bf890b50ee600b56eb02c3a2a1f1913.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "b69668a0743f4bd0acd0904ad145dc684edbaf797eb6e98d367d94f9892ff3ec", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "47a4f7f9a232deb9a375ac58837f7e6bf2aed24d6ecbcb5c51550e372d9d0e6b", "generation_seconds_batch": 17.37943514692597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48385483026504517, "target_z": 0.5273437177361867, "ce": 5.5539960861206055, "genuineness": 4.557555198669434, "identity": 0.8047058582305908, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Dis-moi quand tu es prêt.", "wer": 0.3333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b69668a0743f4bd0acd0904ad145dc684edbaf797eb6e98d367d94f9892ff3ec.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": "b6bd62e7fc847988b7c0cc9b4f39f0636e3290411d5aa76ecab580db6a59ed47", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d41c5003d4a8311969a4f39e1fdfddf97a6f35d05262008cc16aee79de1e58b", "generation_seconds_batch": 23.317640352994204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5049968361854553, "target_z": 0.5664062581734993, "ce": 5.538110733032227, "genuineness": 4.444586753845215, "identity": 0.7347049713134766, "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_Infatuation/b6bd62e7fc847988b7c0cc9b4f39f0636e3290411d5aa76ecab580db6a59ed47.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "b6d4e8402013945314bc0720c35aee1f8f160c2806da5756a402a83f94bfc09b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "26965081bd96f98269d7000bb726edb12a8f4818157bf5ea46d980ed62349068", "generation_seconds_batch": 23.864897417020984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05784386396408081, "target_z": -0.25976563510932815, "ce": 6.0305562019348145, "genuineness": 4.821148872375488, "identity": 0.6125748157501221, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b6d4e8402013945314bc0720c35aee1f8f160c2806da5756a402a83f94bfc09b.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "b6ede820650d70493747061fe686fa177ef8fb5da21438b641e6e99ca4ff9cff", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1dc9f48c533b7e7ce2a2cf0e9294308cf7ef1849f7f5cd6d5154d54cb802caf", "generation_seconds_batch": 24.378000757074915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9553210735321045, "target_z": 1.398437466445634, "ce": 5.208489894866943, "genuineness": 4.162164688110352, "identity": 0.3980931341648102, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b6ede820650d70493747061fe686fa177ef8fb5da21438b641e6e99ca4ff9cff.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "b7e62693401e2c2775a016a03a5427928da5dfd86102bb85e5f4c4ac8f0a024a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "485731d61a51d5af6d98997df0e613b418c01803286c176f3a8f2a7fb8f1bf0b", "generation_seconds_batch": 19.218189920997247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17148202657699585, "target_z": -0.04980470051307138, "ce": 6.133810997009277, "genuineness": 4.821148872375488, "identity": 0.432731568813324, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b7e62693401e2c2775a016a03a5427928da5dfd86102bb85e5f4c4ac8f0a024a.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "b7f82e97894ab23726aea50da4de767d1c617f2bcba86e92538945ff8e1989ba", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b40c3e9ebcd0b95ff58768b5f9896906e9171edae1459dee4869ddfb3ddbdfbf", "generation_seconds_batch": 24.125889193965122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15668264031410217, "target_z": -0.07714844578104542, "ce": 5.677107334136963, "genuineness": 4.6705241203308105, "identity": 0.42072194814682007, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b7f82e97894ab23726aea50da4de767d1c617f2bcba86e92538945ff8e1989ba.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "b8034a9e040bfc6e787658ec0fc9d3b38f4fcf4284ce9d8c8fe9ab6ba09ac181", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5768fe3978ecf3fcba3da111647ca3021c5ecef563ae93389bae143ce50c2bc1", "generation_seconds_batch": 23.708501091925427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004524990916252136, "target_z": -0.3750000137658937, "ce": 6.078212261199951, "genuineness": 4.20609712600708, "identity": 0.7665601968765259, "hypothesis": "De deuren staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b8034a9e040bfc6e787658ec0fc9d3b38f4fcf4284ce9d8c8fe9ab6ba09ac181.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "b824377407fe0ab5fbf069e3a346d432c33c8ab9850ac01a69451108e6473e2e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7a6a0578dc23daac6b9582fcdc4dc025bd7c1a63b072ba292f7bcec6f5befb3d", "generation_seconds_batch": 26.122552737942897, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17518188059329987, "target_z": -0.04296875043018418, "ce": 6.078212261199951, "genuineness": 3.8797430992126465, "identity": 0.17959073185920715, "hypothesis": "The 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_Infatuation/b824377407fe0ab5fbf069e3a346d432c33c8ab9850ac01a69451108e6473e2e.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "b83eec1d68ec166e325f31bd8d4ccd3c271f2dd4c13f3398911d851605f387e2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5999545edd193dc4baa6dc5251f5082c2f5b7764882373f54b21df6c765df4fb", "generation_seconds_batch": 23.982885726029053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06101517379283905, "target_z": -0.25390623752465885, "ce": 6.054384231567383, "genuineness": 4.369274139404297, "identity": 0.6978806257247925, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b83eec1d68ec166e325f31bd8d4ccd3c271f2dd4c13f3398911d851605f387e2.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": "b83f83747cc130f58c05d6cd4011ba8f8e1ef862c1365d4ec719c7a366ac81d2", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "44b5fec845f595283a2e8031e0e3c511dd057e17e7dcda53c197af49d6c3fab6", "generation_seconds_batch": 19.411317800055258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2005680799484253, "target_z": 1.8515624509590038, "ce": 6.340320587158203, "genuineness": 4.2374773025512695, "identity": 0.3261951804161072, "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_Infatuation/b83f83747cc130f58c05d6cd4011ba8f8e1ef862c1365d4ec719c7a366ac81d2.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "b8c4bbdbb1589ccb7459a8a4f2ac725ddff5dee1844bbda6e57d596951109e8f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "715e374b099956ed281b35e4ebdb4302a6cc3b403037bf6ceca75792fb2cad27", "generation_seconds_batch": 25.377681910060346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.043044477701187134, "target_z": -0.2871093803773022, "ce": 6.205295085906982, "genuineness": 4.68307638168335, "identity": 0.7750489711761475, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b8c4bbdbb1589ccb7459a8a4f2ac725ddff5dee1844bbda6e57d596951109e8f.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": "b8dc6eafea27c5058d1ab9e5a16722d70d0e18e77a8b1f26c21c8d664687a268", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5943b31d915e1c38992e0478e56c18da33c4544a176f5d87f3280695fd6e9433", "generation_seconds_batch": 16.88044021592941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4563702940940857, "target_z": 0.47656254732025954, "ce": 6.252951145172119, "genuineness": 4.268857479095459, "identity": 0.25181829929351807, "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_Infatuation/b8dc6eafea27c5058d1ab9e5a16722d70d0e18e77a8b1f26c21c8d664687a268.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": "b90211b9df13808a00e1a36286a705a72363854db688986b6dbcea5eb21e9c30", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fbf6720bde51edc33402942c4d90df8b6b325a2c2495279f34bd6df9650c975", "generation_seconds_batch": 18.042604333953932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.183176189661026, "target_z": -0.028198249352755212, "ce": 5.569881439208984, "genuineness": 4.432034492492676, "identity": 0.7748658061027527, "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_Infatuation/b90211b9df13808a00e1a36286a705a72363854db688986b6dbcea5eb21e9c30.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "b9836f9f146b8fdfab00d0222ecf4ae6ab4f61811344e9fe68985fdc6f5ed041", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "28b615ebb59956cd07c8eb023784f22cdee648d6783f611ba9a4bc7a4ec8691d", "generation_seconds_batch": 26.513833828037605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4648270606994629, "target_z": 0.49218749741889495, "ce": 5.95112943649292, "genuineness": 4.582659721374512, "identity": 0.6471739411354065, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b9836f9f146b8fdfab00d0222ecf4ae6ab4f61811344e9fe68985fdc6f5ed041.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "b9baca88f268ddf036360c2d55610503692df25e35fa9af3bae654232b811349", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1bc6ed5afa0e0c35f99dc604151d05dd13db9e26c3e691eb10bc34b119216177", "generation_seconds_batch": 16.929180564940907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27560630440711975, "target_z": 0.14257812392453956, "ce": 5.418970584869385, "genuineness": 4.356721878051758, "identity": 0.40120333433151245, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b9baca88f268ddf036360c2d55610503692df25e35fa9af3bae654232b811349.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "b9bacb90617e9baaa21309c417d92f02311919ecbc07127db18d55c4f70bf1f8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a221021bf2613eb5e056da83e7ff21d7a96add0d27ab5970caa88bcbb4eefdcc", "generation_seconds_batch": 17.150057859020308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10118493437767029, "target_z": -0.17968750430184177, "ce": 5.498397350311279, "genuineness": 4.507347106933594, "identity": 0.4115106463432312, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b9bacb90617e9baaa21309c417d92f02311919ecbc07127db18d55c4f70bf1f8.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "b9f9632863e4ee24ba2f5f4fd53006fb3632bf0c4335b37b4c568b7ecd5d8b9f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "74487776dd2ca05e2d87b5a40efbd1705e907331a1a8d1be2806fc4b60b82644", "generation_seconds_batch": 23.304559946991503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3337467610836029, "target_z": 0.25, "ce": 6.006728172302246, "genuineness": 4.758388519287109, "identity": 0.619049608707428, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/b9f9632863e4ee24ba2f5f4fd53006fb3632bf0c4335b37b4c568b7ecd5d8b9f.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "ba33900063734881f6c1206ea5fde1f8f16299656bb45647addec9b7ca8b688d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "102ddb4bd62d0017e66dba7986ba730843241cd588395af518ab6fc51cec6527", "generation_seconds_batch": 17.949383190018125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10647043585777283, "target_z": -0.1699218691925136, "ce": 5.847874641418457, "genuineness": 4.557555198669434, "identity": 0.665111780166626, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ba33900063734881f6c1206ea5fde1f8f16299656bb45647addec9b7ca8b688d.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": "ba4864e97b9213eef5184258fb6e02e1ace5d5e781865dee89b1cd8d5d452d8c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15d93e5656352ca25a40d4f8b3f3638565cfe856f96b99da4fa786b7034136cf", "generation_seconds_batch": 25.216837968910113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 6.038498878479004, "genuineness": 4.532451152801514, "identity": 0.5384812355041504, "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_Infatuation/ba4864e97b9213eef5184258fb6e02e1ace5d5e781865dee89b1cd8d5d452d8c.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "ba6d86abc4ccb529855f0521710248fa4e2bffc09e2364c63c111c4c18932adc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0332be88e6a55a6b02097c3f78b8ddea4b388c085b5ab342895dcf0852cf7555", "generation_seconds_batch": 25.787922274903394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09537088871002197, "target_z": -0.19042969190938783, "ce": 6.1894097328186035, "genuineness": 4.632867813110352, "identity": 0.7682429552078247, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ba6d86abc4ccb529855f0521710248fa4e2bffc09e2364c63c111c4c18932adc.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "2bd0fc6485fac668ae506cd64a60817e0320109e2415e12f2874ef905b68a64e", "generation_seconds_batch": 16.877082854975015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030359283089637756, "target_z": -0.3105468881206174, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.7211352586746216, "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_Infatuation/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.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": "ba77cca68b27c6494be2b88b7848637d0c221ada568221338691571d578ca3d3", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8257011cd2ab6c7ddf92888cfed1a921735c0cadad750de09d604318961dae17", "generation_seconds_batch": 23.724474738002755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010867580771446228, "target_z": -0.3867187538716576, "ce": 6.205295085906982, "genuineness": 4.457139015197754, "identity": 0.4352150559425354, "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_Infatuation/ba77cca68b27c6494be2b88b7848637d0c221ada568221338691571d578ca3d3.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "bab1565c07bf315deebd77cb746353c4b6be977250316276a7df9ceb0407c793", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d290cbcc47f1c7b707f7649f8d9c1b6788b3d428c791ea47e861187438bff557", "generation_seconds_batch": 18.932285959017463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4521418809890747, "target_z": 0.4687500172073671, "ce": 5.804190158843994, "genuineness": 3.9173994064331055, "identity": 0.25244957208633423, "hypothesis": "The 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_Infatuation/bab1565c07bf315deebd77cb746353c4b6be977250316276a7df9ceb0407c793.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "bb56e7156fd914791bc137efb22674b12a3ad8e818bbfc1cd3f6a98f53432c7b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94f162ecc3587ba01a82df4aeda691b31c5ac0124a858db22d524272101d070b", "generation_seconds_batch": 18.249701819964685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2238084375858307, "target_z": 0.046874987954843024, "ce": 5.7128496170043945, "genuineness": 4.293961524963379, "identity": 0.6594251394271851, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bb56e7156fd914791bc137efb22674b12a3ad8e818bbfc1cd3f6a98f53432c7b.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "bbeb97a9659ad309d62494909653f8442b1fd42152b3b3dab499b826ea2be38b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e237cbe108a6a0a5b77a04795d815a06b51d13323cee9ddae07f33305795f865", "generation_seconds_batch": 23.384911539964378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8115555644035339, "target_z": 1.1328124337516365, "ce": 5.772419452667236, "genuineness": 4.519899368286133, "identity": 0.6168770790100098, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bbeb97a9659ad309d62494909653f8442b1fd42152b3b3dab499b826ea2be38b.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "bc4dc9f353c9b4521b4d75d5425d017983378cd21fc4dea59468130f83ecfe86", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be18dc30b2c8016b07df3b4a4fd056fdebb87af8a6e910b9fc0519aa7e886902", "generation_seconds_batch": 17.15901657694485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1692356914281845, "target_z": -0.05395508992817838, "ce": 5.5659098625183105, "genuineness": 4.632867813110352, "identity": 0.7181805372238159, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bc4dc9f353c9b4521b4d75d5425d017983378cd21fc4dea59468130f83ecfe86.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "bc6900b289bc6645b2e6f22a8ddbfe5757e50ce8f69a458cac3fa2e3414e5a6e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "55ad775ba053a6f7b2a6cf1a42917be834dc77de93ff75918de23289eb408c46", "generation_seconds_batch": 23.755367582081817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01721017062664032, "target_z": -0.3984374939774215, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.5249297618865967, "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_Infatuation/bc6900b289bc6645b2e6f22a8ddbfe5757e50ce8f69a458cac3fa2e3414e5a6e.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": "bca4a0ee3e300d60124ae04f8d3b46a338117f9be7020b5d24789a158a1ba0b2", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e2cb2e6c8ea99aca6c413611861d5edac87db9e80a35c3f355dce7ca14cd161", "generation_seconds_batch": 17.39164016302675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5113394260406494, "target_z": 0.5781249982792633, "ce": 5.919358730316162, "genuineness": 4.482243061065674, "identity": 0.7326240539550781, "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_Infatuation/bca4a0ee3e300d60124ae04f8d3b46a338117f9be7020b5d24789a158a1ba0b2.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "bcbcc7ea780f56af75c148b20cdcf2275d5c3024d8d7600910b82192369e11f8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0a7f27276e109f725ef8277a191daeafa6c7cc8399447a3b71067895532e0326", "generation_seconds_batch": 23.57174812804442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08162859827280045, "target_z": -0.21582031841503244, "ce": 6.133810997009277, "genuineness": 4.68307638168335, "identity": 0.7277551889419556, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bcbcc7ea780f56af75c148b20cdcf2275d5c3024d8d7600910b82192369e11f8.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": "bcc5a29d3e8e4fad9258fdd7bf41ec37ce98200757299c6c3c9e52bc9a7443db", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a416d8e35245b53a8d1d7853f56ed321e65899dad46d47fc65933a66ce328c8", "generation_seconds_batch": 24.948952112928964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 6.062326908111572, "genuineness": 4.808597087860107, "identity": 0.7623202204704285, "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_Infatuation/bcc5a29d3e8e4fad9258fdd7bf41ec37ce98200757299c6c3c9e52bc9a7443db.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "bcd905438afed3e94a63de3f0989d2cb4b54f3965fb87217ef1069be89a20b9f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "072e3a16f976ad703357d10249ab1a4dd864540bf66745fccfd74f3c3e97c030", "generation_seconds_batch": 24.54299266601447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22433699667453766, "target_z": 0.04785156798484826, "ce": 5.371314525604248, "genuineness": 4.469690799713135, "identity": 0.7263042330741882, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bcd905438afed3e94a63de3f0989d2cb4b54f3965fb87217ef1069be89a20b9f.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "bd98806f95d73de269a09c6735c23592c8b50025046ba3be964c65fe5142d890", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "189cbaf2025c3ebab54505912d17d68738ccc5a302de590ac05ffdbbb276edfb", "generation_seconds_batch": 26.13558955094777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23120814561843872, "target_z": 0.06054688812061742, "ce": 6.09409761428833, "genuineness": 4.20609712600708, "identity": 0.7607908844947815, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bd98806f95d73de269a09c6735c23592c8b50025046ba3be964c65fe5142d890.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "be472a5a9b8831f78cd65d62843ff56a3374a57b52a3593f35e62e8aa05634fd", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14154d036f6259f98a0ad8157de931f97affc18c1a0365c5ba6f5c91ab89f650", "generation_seconds_batch": 24.708613186026923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 6.1020402908325195, "genuineness": 4.909013748168945, "identity": 0.7156294584274292, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/be472a5a9b8831f78cd65d62843ff56a3374a57b52a3593f35e62e8aa05634fd.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "bea99d5cf92dde68d5cc2d1ee0ebbf10be1e227110ebe8dec0adce224d9aa14f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1b147335f0144643684a3e9fcf385d0ae840b7ed9a676fd08d39b9ea924577fe", "generation_seconds_batch": 25.858876965008676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.021902501583099365, "target_z": -0.3261718657510402, "ce": 6.038498878479004, "genuineness": 4.218649387359619, "identity": 0.525107741355896, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bea99d5cf92dde68d5cc2d1ee0ebbf10be1e227110ebe8dec0adce224d9aa14f.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "bf15f922d01b06f95035c5d0006ef9fbbfeb5309bbcdbcc2ffd39685d81fd468", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "28e03a15004bda46b14361f274316264e1fa6281b6aa580630e98d5706ee970f", "generation_seconds_batch": 23.469351275009103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05361546576023102, "target_z": -0.26757813769043326, "ce": 5.808161735534668, "genuineness": 4.061748504638672, "identity": 0.5023666024208069, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bf15f922d01b06f95035c5d0006ef9fbbfeb5309bbcdbcc2ffd39685d81fd468.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "bf659df1123a41d117f10799d2f4bd933e81dd39a6252090e63811487e4f6eff", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fff6851c997732d5fae6339e1243ca4d72801ec5e9d58bc56615594755621804", "generation_seconds_batch": 23.71452081494499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2808918058872223, "target_z": 0.15234375903386774, "ce": 6.419747352600098, "genuineness": 4.545003414154053, "identity": 0.48369842767715454, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/bf659df1123a41d117f10799d2f4bd933e81dd39a6252090e63811487e4f6eff.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "c01bcbca40c9bef3a4b95d5a5e4dd5d5e3d7a39ff695c82e13a442fdaaf13bf4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "19d8369c71539936b56387da3d83913b1489fad2aa509b3074e8b270faa41d40", "generation_seconds_batch": 23.137905756011605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07158616185188293, "target_z": -0.23437499483778987, "ce": 6.109982967376709, "genuineness": 3.7291181087493896, "identity": 0.15957710146903992, "hypothesis": "The 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_Infatuation/c01bcbca40c9bef3a4b95d5a5e4dd5d5e3d7a39ff695c82e13a442fdaaf13bf4.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "c0477f7fbe85dfb18420be0f85aeabaaf7d1fd839fd62e60534b15f51fcbf865", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0f6356ea77226fa48e659602ca2530e5e692c0fced9f8a9a909308aa268c8656", "generation_seconds_batch": 25.828103650943376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198737442493439, "target_z": -0.2890625129055253, "ce": 5.395142555236816, "genuineness": 4.13078498840332, "identity": 0.4130837619304657, "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_Infatuation/c0477f7fbe85dfb18420be0f85aeabaaf7d1fd839fd62e60534b15f51fcbf865.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "c13e5cfd593736060b13cf8cb857e545addbafb796ee01d5ce337fd7c215f273", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "38f6698a6839e80949e6fb38b261c35412c61dbc4ec758c9f94ea1b43917a9a4", "generation_seconds_batch": 24.492326147970743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5303671956062317, "target_z": 0.613281218596555, "ce": 6.221180438995361, "genuineness": 4.632867813110352, "identity": 0.388801634311676, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c13e5cfd593736060b13cf8cb857e545addbafb796ee01d5ce337fd7c215f273.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "c14ca3ccd6a46259fc222c71480d9cf4e0a389f901bb8bd270af682a5cf75de7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0988fcdd966232e59319bdadf6ab4fd9050e8655d5c730babfbe60697d7f4e6c", "generation_seconds_batch": 26.0542494780384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017674103379249573, "target_z": -0.33398436833214523, "ce": 5.9431867599487305, "genuineness": 4.381826400756836, "identity": 0.583836555480957, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c14ca3ccd6a46259fc222c71480d9cf4e0a389f901bb8bd270af682a5cf75de7.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": "c26e498228a5b3e555331508806983e423ef141205d360fd2cc4e00b4caa7191", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "13fa4a8e6e229430fff304bf24ad019fed5a1a50c29503f9d634c2767f5a1af0", "generation_seconds_batch": 18.85514882497955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0034678876399993896, "target_z": -0.3730468812376706, "ce": 6.054384231567383, "genuineness": 3.9299514293670654, "identity": 0.42040809988975525, "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_Infatuation/c26e498228a5b3e555331508806983e423ef141205d360fd2cc4e00b4caa7191.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "c26f2cb962c3cb0d5c208aa52b62f78f77771905eed4f09b7e7ba0e678dbf0a3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "915ff958674023b1bfe7be542af6ddf649d7ad827db0ec173c56cf447d455239", "generation_seconds_batch": 30.074936847086065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3665168285369873, "target_z": 0.31054686058883, "ce": 6.3641486167907715, "genuineness": 4.457139015197754, "identity": 0.29604023694992065, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c26f2cb962c3cb0d5c208aa52b62f78f77771905eed4f09b7e7ba0e678dbf0a3.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "c3281ce07967657192487b2ae6659b58b2dfd92b749d8c4dafd52205a91bd5d5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5477b82590ce287146c82310de61b8b829c600733fdf72b2e895d16167785248", "generation_seconds_batch": 23.648502427968197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24125057458877563, "target_z": 0.07910155077748116, "ce": 5.911416053771973, "genuineness": 4.457139015197754, "identity": 0.7546393275260925, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c3281ce07967657192487b2ae6659b58b2dfd92b749d8c4dafd52205a91bd5d5.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "c387145668509520582514f63b0b9bc6821a10f74b6df5540f7055e9aaf21597", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6f6ac18ad757831e87060efd819b8b99adc7183e8926f8c5c0de35c0eb4af969", "generation_seconds_batch": 29.542537412955426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2113875299692154, "target_z": 0.02392578399242413, "ce": 6.125868320465088, "genuineness": 4.262581825256348, "identity": 0.5217328071594238, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c387145668509520582514f63b0b9bc6821a10f74b6df5540f7055e9aaf21597.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "2e165c0e4737864d8d2fb0e019f95794d5b410f60a2c80392e6663f7e7ddecd9", "generation_seconds_batch": 20.598119886941276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.047272875905036926, "target_z": -0.27929687779619716, "ce": 6.141753673553467, "genuineness": 4.469690799713135, "identity": 0.6618527173995972, "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_Infatuation/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "c39c1a46e9063048e342bdcec105eb2bc1364da7798bd808fff03413ec9038c4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "34d33c130be746237b2f1732ead2080490f75f1017ca49a2e7598a523af25534", "generation_seconds_batch": 19.95846700889524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05890096724033356, "target_z": -0.25781250258110505, "ce": 6.0305562019348145, "genuineness": 4.457139015197754, "identity": 0.7150111198425293, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c39c1a46e9063048e342bdcec105eb2bc1364da7798bd808fff03413ec9038c4.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "c3a295aa6cdc710c8b3029937920a3631040621aaa79d2f4ffe81965fb9d426e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "23bf7801de2bac72d4cede52b6ead5cd0f95d4d86d2fd4694b4cf8b0b14093b1", "generation_seconds_batch": 22.788213610067032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6847037076950073, "target_z": 0.8984375215092089, "ce": 6.109982967376709, "genuineness": 4.149612903594971, "identity": 0.363057941198349, "hypothesis": "The 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_Infatuation/c3a295aa6cdc710c8b3029937920a3631040621aaa79d2f4ffe81965fb9d426e.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "c3b5383ac260595c4376c2cbc14ca1c3024b616b6eea841489d2caff213ba27b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c229479c88ac5488588fed21fdbf9a9794952b640780a366b019453a289c2d9d", "generation_seconds_batch": 23.65195850096643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10805608332157135, "target_z": -0.16699218416607262, "ce": 6.006728172302246, "genuineness": 4.632867813110352, "identity": 0.5658801794052124, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c3b5383ac260595c4376c2cbc14ca1c3024b616b6eea841489d2caff213ba27b.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": "c42204f25a11bd2fb35fbef62c07b34d2f5be3d1d8019ee3493d842cb5203694", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "9a21bde77536beb7c8a50a0557237c8c5e53e7ded0070a56984db99dea056aa7", "generation_seconds_batch": 18.462183596100658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13712631165981293, "target_z": -0.1132812461283424, "ce": 5.895530700683594, "genuineness": 4.557555198669434, "identity": 0.790346622467041, "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_Infatuation/c42204f25a11bd2fb35fbef62c07b34d2f5be3d1d8019ee3493d842cb5203694.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "c43a6f79945b521642a963aad302419ba9407149dfdcb136ad4e413ba89692fa", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f99058d88f70f06fb9261d7816e10e7f999ffabaabcd9c634b1c86b4ecf1a695", "generation_seconds_batch": 17.800545614096336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0034678876399993896, "target_z": -0.3730468812376706, "ce": 5.974957466125488, "genuineness": 4.6203155517578125, "identity": 0.68999183177948, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c43a6f79945b521642a963aad302419ba9407149dfdcb136ad4e413ba89692fa.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "c458e37954cc760f1bc78e750a3756d170c8d4ab49705904cdc4124d367b244b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "01ccb79db7fe18f587722391460ac3cd1c2e54cee13a5e8ac4bad745292287cb", "generation_seconds_batch": 23.94316853804048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.016153067350387573, "target_z": -0.3964843614491984, "ce": 6.006728172302246, "genuineness": 4.337893962860107, "identity": 0.3392114043235779, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c458e37954cc760f1bc78e750a3756d170c8d4ab49705904cdc4124d367b244b.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "c4697b250a1638a2795905ec99acf09aefb5de11da30242767fe6b384b9348f1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e025f3147502c0cf3e36d2d264f04c4b8b4e316dbdfeabe96954a14842831aa0", "generation_seconds_batch": 17.67698481096886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20861265063285828, "target_z": 0.018798842079099265, "ce": 5.071478843688965, "genuineness": 4.137060642242432, "identity": 0.5409390926361084, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c4697b250a1638a2795905ec99acf09aefb5de11da30242767fe6b384b9348f1.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "0b947a5d0c0da9fcb3b8b36a178f15c3756a7fa99e615fb292d2aef7a0130c6f", "generation_seconds_batch": 17.860208133002743, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024016693234443665, "target_z": -0.32226562822638133, "ce": 6.356205940246582, "genuineness": 4.557555198669434, "identity": 0.5039332509040833, "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_Infatuation/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "c50065dc9d26ca872a9ab924883b0f2f33cc4257f4d82644080c2ca4dde0f3f5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f7ba31f1b78699466d26f3e9b1f2d09bf67f2b1b0cd6ffa8034ad7f805c42dde", "generation_seconds_batch": 23.954445051960647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2600140869617462, "target_z": 0.11376952237745133, "ce": 6.062326908111572, "genuineness": 4.105680465698242, "identity": 0.3630022704601288, "hypothesis": "The 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_Infatuation/c50065dc9d26ca872a9ab924883b0f2f33cc4257f4d82644080c2ca4dde0f3f5.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "c58c27e70db85e04ff5a42993e18c4f181556b76f4238497859f8769c2ea0c46", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "47cc998b6efa373ad6df2e70783452d5bc18c399047548a0d0773c884fd65bdc", "generation_seconds_batch": 24.828052781056613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0018176138401031494, "target_z": -0.3632812461283424, "ce": 6.046441555023193, "genuineness": 4.055472373962402, "identity": 0.6728076934814453, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c58c27e70db85e04ff5a42993e18c4f181556b76f4238497859f8769c2ea0c46.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "c5b8033a9f58102f29ceef0cc4b6bab10498c0638bec0721870a34f6b757cecb", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a92e4ff3905949c11f3d6dc02e35cb08b4b49f4b8601ab35f27b0e6adfcca94e", "generation_seconds_batch": 28.91577992902603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09907073527574539, "target_z": -0.1835937555923943, "ce": 5.927301406860352, "genuineness": 4.243753433227539, "identity": 0.5257217884063721, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c5b8033a9f58102f29ceef0cc4b6bab10498c0638bec0721870a34f6b757cecb.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": "c60033066c261b268c52d84b0f472f55239143d4208fb41337cc6724dbf8c214", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38c62a83b60d51ecec19513baeac5bce919f67ea633f87ea7694f136171bc65c", "generation_seconds_batch": 23.410479686921462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008753374218940735, "target_z": -0.3828124888152114, "ce": 5.152891159057617, "genuineness": 3.8797430992126465, "identity": 0.3925189971923828, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la. En daarna, naast dit gaam, neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c60033066c261b268c52d84b0f472f55239143d4208fb41337cc6724dbf8c214.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": "c68d5ee6a47757bcce5e743a6f3908daf1a702e0d238388752f7592b60479213", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95407a435e59a678fcda38392cc22cec30f12a657223f826b9695229a7a9a50e", "generation_seconds_batch": 16.594881839933805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.021438568830490112, "target_z": -0.40624999655852656, "ce": 6.109982967376709, "genuineness": 4.545003414154053, "identity": 0.46672481298446655, "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_Infatuation/c68d5ee6a47757bcce5e743a6f3908daf1a702e0d238388752f7592b60479213.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "c7047b83401aa5e8de323b29af91a6eaced822feb6f03b6a556f289c86f68090", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1713273716f70d3554b743ffa72039804aa691179c88d12fc82a0c76d1f6684f", "generation_seconds_batch": 23.322871427051723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029302194714546204, "target_z": -0.3124999931170532, "ce": 6.006728172302246, "genuineness": 4.287685871124268, "identity": 0.5927675366401672, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c7047b83401aa5e8de323b29af91a6eaced822feb6f03b6a556f289c86f68090.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "c7461c8a7a1bb9189915c16fd2cf8dc8bc5198879ae5ed6ffdc65634e817e733", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0ecdc5bae3c3ad5c89ec817b54c1736f90b76eb53b841793d3af40b9bda23235", "generation_seconds_batch": 19.316732804989442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.7351595759391785, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c7461c8a7a1bb9189915c16fd2cf8dc8bc5198879ae5ed6ffdc65634e817e733.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": "c775ae7229c6ba71968115af096216757daf01b84bbd0a962c48e8d01e5bce1d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "236b33779bec29ca415bd67f40df212b9e4ce1af8fcfe3f2b6b6941309ff763d", "generation_seconds_batch": 25.965201972983778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2247334122657776, "target_z": 0.04858399612440535, "ce": 6.332377910614014, "genuineness": 4.519899368286133, "identity": 0.4726376533508301, "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c775ae7229c6ba71968115af096216757daf01b84bbd0a962c48e8d01e5bce1d.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "c7e4e7556265d7793bf4c927644e55132bd5abb32ed55e586a20bab8c7c13a36", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "df14c0fe81db5a1c5668d1b2feccf0a06d0322edb19246ad73b02474c614c388", "generation_seconds_batch": 17.37943514692597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4605986475944519, "target_z": 0.4843749673060025, "ce": 5.756534099578857, "genuineness": 4.645420074462891, "identity": 0.7838050127029419, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c7e4e7556265d7793bf4c927644e55132bd5abb32ed55e586a20bab8c7c13a36.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "c7e9653c0a0efd043d15aaa873c2ee0b4903e9634ad45822e5213cf734b63326", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cd668dff3320d93206a526bb4b8efadc1361b4b2f72df9f918fb7ef261137d3", "generation_seconds_batch": 26.513833828037605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7185308337211609, "target_z": 0.9609374320308999, "ce": 6.0146708488464355, "genuineness": 4.758388519287109, "identity": 0.6961965560913086, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c7e9653c0a0efd043d15aaa873c2ee0b4903e9634ad45822e5213cf734b63326.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "4676f27a621ba5d7f16392d8bac154fe4de1f9b01e2465e9522a489d24601493", "generation_seconds_batch": 17.60671513399575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014502808451652527, "target_z": -0.3398437383850272, "ce": 6.229123115539551, "genuineness": 4.507347106933594, "identity": 0.6994100213050842, "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_Infatuation/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "heldout-en-3", "language": "en", "sentences": [ "Someone moved the little blue chair.", "It used to stand here... beside the tall bookshelf.", "We can put it back after lunch." ], "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-en-3", "key": "c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "35d783a81113a2d257f13e602704b881274ae85e91412cc56880aaabaaa8b0e2", "generation_seconds_batch": 19.495055604027584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08374279737472534, "target_z": -0.2119140671244799, "ce": 6.459460258483887, "genuineness": 4.293961524963379, "identity": 0.46968942880630493, "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_Infatuation/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "c93211cfab2b4546c734f3255f740f80357f14ee22afd3f7fa84749e275f9ee5", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "29a992e745388ee61dc98c76c7b0aa858e3c5c6e03f7e745b15956e6d579b359", "generation_seconds_batch": 23.853357588057406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29410552978515625, "target_z": 0.17675779174361342, "ce": 6.316492557525635, "genuineness": 4.582659721374512, "identity": 0.3766619861125946, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c93211cfab2b4546c734f3255f740f80357f14ee22afd3f7fa84749e275f9ee5.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": "c9573b1dd60e550888126e959ce5c91061e5464abcb7ae79ede977ceb4bef850", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04d8bc493c8e906ab03bb465d42296d5941c933745c6444d50e67a2d585898dd", "generation_seconds_batch": 18.041061292984523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04832997918128967, "target_z": -0.27734374526797406, "ce": 5.311744689941406, "genuineness": 4.306513786315918, "identity": 0.7117892503738403, "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_Infatuation/c9573b1dd60e550888126e959ce5c91061e5464abcb7ae79ede977ceb4bef850.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": "c960a1a9370b8c36a92bb0883c48a16b96c60c1012bb2ad3402020257346cf1c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1a6800b6ff1b0619ffa99cbcedc31fb6b2aeb3cd2df19f079807f92ece0c16c", "generation_seconds_batch": 23.74490503896959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20511099696159363, "target_z": 0.012329092300096923, "ce": 6.109982967376709, "genuineness": 4.595211505889893, "identity": 0.3793981075286865, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en leg mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/c960a1a9370b8c36a92bb0883c48a16b96c60c1012bb2ad3402020257346cf1c.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": "ca3fde65ea06fcc40371549f45fc24610f4f9892ceddec53e59a3c7fae92990b", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "2f76d301a783205b47cfc57228c158745459782c9d25e10babd9d03a272224db", "generation_seconds_batch": 18.99105284595862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3221186697483063, "target_z": 0.22851562478490792, "ce": 6.356205940246582, "genuineness": 4.231201171875, "identity": 0.32115140557289124, "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_Infatuation/ca3fde65ea06fcc40371549f45fc24610f4f9892ceddec53e59a3c7fae92990b.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "ca49675a5dc44b11f08e340a295eedac67d0f35a49c761729265e0a87394cf7e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f7595ca640718d785ddf16b006c94cea085e1b4ab2dd82d802094b7f1a4bf76a", "generation_seconds_batch": 24.020623928983696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12391257286071777, "target_z": -0.13769530636987548, "ce": 6.054384231567383, "genuineness": 4.582659721374512, "identity": 0.7879458665847778, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ca49675a5dc44b11f08e340a295eedac67d0f35a49c761729265e0a87394cf7e.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "ca78ca3112c86141094c8a30e1913ddf527d6e89c2e777bc898e5a2374164449", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a92a3705471f6e36dae42321feacd9b71928a3613e83b922ee3a5f3779d40911", "generation_seconds_batch": 21.700005023973063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18945272266864777, "target_z": -0.016601557660428, "ce": 6.117925643920898, "genuineness": 4.833701133728027, "identity": 0.7839426398277283, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ca78ca3112c86141094c8a30e1913ddf527d6e89c2e777bc898e5a2374164449.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": "ca8691c2faf394fd165364c7b4d3370ef7055af0cbaaa34c8b24e387333d316c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "464f0b18adfc657f5e4bdbe0a833ce467222ddbb29fa15aa250433919ea2d1c5", "generation_seconds_batch": 16.594881839933805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02249567210674286, "target_z": -0.40820312908674966, "ce": 5.967014789581299, "genuineness": 4.469690799713135, "identity": 0.41517430543899536, "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_Infatuation/ca8691c2faf394fd165364c7b4d3370ef7055af0cbaaa34c8b24e387333d316c.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "ca8cec5e906995b49c92eca54366c500bb2db8bbc2a552ec7005e9308b8e160d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63624eee57f1c29b385b795259cd8f4350d34cdd1c6e6168e5f23babacab90a9", "generation_seconds_batch": 17.129387527005747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0066391825675964355, "target_z": -0.37890625129055255, "ce": 6.078212261199951, "genuineness": 4.607763767242432, "identity": 0.6553158760070801, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ca8cec5e906995b49c92eca54366c500bb2db8bbc2a552ec7005e9308b8e160d.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "cb00baf0fe3f72f415777d389eed30e75b14c3b3037cb3d0e2f89e78bb34fb6b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a79cd56d8bb06854e66e5dedbe280a89e0444970d9918e260ae8e7c2570db9a7", "generation_seconds_batch": 24.71873175993096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24944309890270233, "target_z": 0.09423827969058235, "ce": 6.006728172302246, "genuineness": 4.770940780639648, "identity": 0.6246160268783569, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cb00baf0fe3f72f415777d389eed30e75b14c3b3037cb3d0e2f89e78bb34fb6b.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "cb148a076f8ef048fbaa02f0f27c976d1d813689deffe98811ec44cc1a4f9085", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "56a02411580162b9f87891eb067f9cdd6e68191ebe1b9a049a8e748f3aa945f9", "generation_seconds_batch": 16.744452214916237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02249567210674286, "target_z": -0.40820312908674966, "ce": 5.704906940460205, "genuineness": 4.557555198669434, "identity": 0.03528206795454025, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cb148a076f8ef048fbaa02f0f27c976d1d813689deffe98811ec44cc1a4f9085.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "cb192468bacabee587e207d8a46e9bf7fdc73b4a4238e8af5457f9354ff9b117", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "62ec35aeebffb6170a5405b624313512176d5568a558573446f8bd3cd94f7f20", "generation_seconds_batch": 23.294352906988934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6635617017745972, "target_z": 0.8593749810718961, "ce": 6.157639026641846, "genuineness": 4.570107460021973, "identity": 0.4898766279220581, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cb192468bacabee587e207d8a46e9bf7fdc73b4a4238e8af5457f9354ff9b117.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "cb1b6329255a90e059824dc253d0dca02c378a9e731d3c121521c8bb004fbae2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4a47f9f0063b44273e8156ce1af963422759599e8fc17776c234b68917dc3238", "generation_seconds_batch": 17.15901657694485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1212698221206665, "target_z": -0.14257812392453956, "ce": 5.744620323181152, "genuineness": 4.482243061065674, "identity": 0.7722126245498657, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cb1b6329255a90e059824dc253d0dca02c378a9e731d3c121521c8bb004fbae2.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "cb5ad2e8a06fa4b8de082d7f1d08061ba98b6735655754709150e4d612e5601a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ecae2badc3c78c0f5700b821e069e2d6afbe99e0075240b5978db4bfb8a6cf68", "generation_seconds_batch": 17.150057859020308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 5.434855937957764, "genuineness": 4.507347106933594, "identity": 0.5618088245391846, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cb5ad2e8a06fa4b8de082d7f1d08061ba98b6735655754709150e4d612e5601a.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "ccf2340e36703b92df88708c946b82c1859fcd2c903e394e87fec656199339c8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1ebb6ac2c9d16c55b0263f2997f77dcd83b7f311ddc8fd66323772c0c64371a4", "generation_seconds_batch": 23.120152138988487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03247348964214325, "target_z": -0.3066406230641712, "ce": 6.125868320465088, "genuineness": 4.494794845581055, "identity": 0.595505952835083, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ccf2340e36703b92df88708c946b82c1859fcd2c903e394e87fec656199339c8.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "cd6e2779d63ea69956ada93a1c76792fb35a6468db4cd132a10071adff1c8b3c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ecdc1de0c1152003ca903b7c51d92ae1fd11994f250104351e1aa15ee472916c", "generation_seconds_batch": 24.06297988409642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004524990916252136, "target_z": -0.3750000137658937, "ce": 6.284721851348877, "genuineness": 4.607763767242432, "identity": 0.6341134309768677, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cd6e2779d63ea69956ada93a1c76792fb35a6468db4cd132a10071adff1c8b3c.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "cdb180a16b94e3dc70e29d55fec42cdbf860229fdb99acda0435d4d8fdda828c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "96807732bd558f29016b9bd496519e151a3e069d0f208f8d483e7b48f8841641", "generation_seconds_batch": 24.116994161973707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11069882661104202, "target_z": -0.16210938037730221, "ce": 5.665193557739258, "genuineness": 4.582659721374512, "identity": 0.6462402939796448, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cdb180a16b94e3dc70e29d55fec42cdbf860229fdb99acda0435d4d8fdda828c.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "cdca56412b2601c6b8dba612d4a5bf43a0f62e7ad67dee6219d7b7450039ba7c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1092dec243958fbb3e11cdb4df96d572f0cc38ecc02c3324a421471e79a129c5", "generation_seconds_batch": 26.407272892072797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03458768129348755, "target_z": -0.3027343855395124, "ce": 5.935244083404541, "genuineness": 4.256305694580078, "identity": 0.4101310074329376, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cdca56412b2601c6b8dba612d4a5bf43a0f62e7ad67dee6219d7b7450039ba7c.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": "ce1ea6362b3b34ebefca786f0273290ececce8d2c2551e50cf8e0c24dff9cb2e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "decf2339352faff8f107092d2f61609bc16a1cb25db1c7a12ad95db702d23fed", "generation_seconds_batch": 16.670864054001868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010274410247802734, "target_z": -0.3476562409661323, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.6889357566833496, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier. Naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ce1ea6362b3b34ebefca786f0273290ececce8d2c2551e50cf8e0c24dff9cb2e.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": "ce8b3ea02274c4d9d7acb86d9149c8a7ea921293a64c0944cae7344df3eec7eb", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "acde3b6f7b3c153fe45d160c1f87688e7f04247fc5b3049a0497e7b8ccd83533", "generation_seconds_batch": 17.106556372949854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7016172409057617, "target_z": 0.9296874217064797, "ce": 6.109982967376709, "genuineness": 4.796044826507568, "identity": 0.696364164352417, "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_Infatuation/ce8b3ea02274c4d9d7acb86d9149c8a7ea921293a64c0944cae7344df3eec7eb.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "369c157528a18a8ded32bd5d16e605d759b9800c90db71feb662a42cbc9b0f64", "generation_seconds_batch": 18.079500308958814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052558377385139465, "target_z": -0.26953124268686895, "ce": 6.38003396987915, "genuineness": 4.482243061065674, "identity": 0.454897403717041, "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_Infatuation/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "cf7d322999d9ebb56ad6b3e549e4a1ac7235ea57119e4d7bc0c0e98ada711d8b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "06ba6962e14a0a834999d99750b67ad693e11df6ee3041bd11938d4ec18ff883", "generation_seconds_batch": 23.321421329979785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017674103379249573, "target_z": -0.33398436833214523, "ce": 6.173524379730225, "genuineness": 4.582659721374512, "identity": 0.6896636486053467, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/cf7d322999d9ebb56ad6b3e549e4a1ac7235ea57119e4d7bc0c0e98ada711d8b.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "cfd3b47e234879dabc1896a9c7fedba698cbfac69190c9becccc94957ede9bc8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "12f3b68ad36efb49199ef4aeab78ea661f2193948beb155d482a421b355d0cbe", "generation_seconds_batch": 23.88752032094635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030359283089637756, "target_z": -0.3105468881206174, "ce": 6.070269584655762, "genuineness": 4.419482707977295, "identity": 0.44976237416267395, "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_Infatuation/cfd3b47e234879dabc1896a9c7fedba698cbfac69190c9becccc94957ede9bc8.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": "d0dd7f6846c5fd2434ff4a3a5f2f5269c6c2ca7ed08155c1fa2440d635919040", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1afa00d723917159fe4e1c16e175bc0abd34d3ccf2fdee1a7304cb4ea9dbe6f6", "generation_seconds_batch": 17.927096002968028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06365790963172913, "target_z": -0.24902344750178212, "ce": 5.383228778839111, "genuineness": 4.20609712600708, "identity": 0.6808299422264099, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Pend-les quand tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d0dd7f6846c5fd2434ff4a3a5f2f5269c6c2ca7ed08155c1fa2440d635919040.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "d0f815fbeaa007d0ee87637f57494f141515e35246adae931064990b671cd2bf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9f7d298067cad2a8e5bf448fbee8cca9ddbf0bd70927715cf4b19ecfbc48120f", "generation_seconds_batch": 25.04692650400102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3601742386817932, "target_z": 0.2988281204830661, "ce": 6.006728172302246, "genuineness": 3.911123275756836, "identity": 0.42241835594177246, "hypothesis": "The 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_Infatuation/d0f815fbeaa007d0ee87637f57494f141515e35246adae931064990b671cd2bf.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": "d117b001ebc4db18c660fe5c44a27cfad1775ad937de7a99f76a5bb6abe7c71c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "904e70a53d208d6985810d19a38eb517024364294cc9047d99b5a6e3358351e2", "generation_seconds_batch": 19.158219364006072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014502808451652527, "target_z": -0.3398437383850272, "ce": 6.1894097328186035, "genuineness": 4.444586753845215, "identity": 0.64620441198349, "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_Infatuation/d117b001ebc4db18c660fe5c44a27cfad1775ad937de7a99f76a5bb6abe7c71c.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7e687b12f2e1ba02fd97e4e14046eae0b81ce5607a3dbbdeee2def2c0666c477", "generation_seconds_batch": 20.152974365046248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01344570517539978, "target_z": -0.34179687091325034, "ce": 6.435632705688477, "genuineness": 4.042920112609863, "identity": 0.3327813148498535, "hypothesis": "I wrote the number on the envelope, read it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "d14adda7019a4fb0021411842b0d90485b1592c1213d7469608f8c1f634cda97", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "51069781cb90e7d087a716370aaa10ed837a122461a63270dec781394f7417e2", "generation_seconds_batch": 24.59163495793473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1907740980386734, "target_z": -0.014160148883095957, "ce": 6.435632705688477, "genuineness": 4.68307638168335, "identity": 0.3789045810699463, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d14adda7019a4fb0021411842b0d90485b1592c1213d7469608f8c1f634cda97.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "d1e34e51d1d17f4d7f7aaf9132ca85f1bb8261bf28881d703563d45514fc88dc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "921be4d8e6cf550601127c7f0c3a9c9570569cdc899a6afdf0f4669377f37fc5", "generation_seconds_batch": 23.378950819023885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19090622663497925, "target_z": -0.013916024524435177, "ce": 5.772419452667236, "genuineness": 4.808597087860107, "identity": 0.8662676811218262, "hypothesis": "J'ai trouvé la 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_Infatuation/d1e34e51d1d17f4d7f7aaf9132ca85f1bb8261bf28881d703563d45514fc88dc.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": "d1f87db6080ebc3c3bfac94000f1a3ffde3062f9b50e91ecc8e6b4009cf45515", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1df3fdce745a5b52b16baea8f64eb357c878ab19c52f72b48e88d1a2de27c17", "generation_seconds_batch": 18.321385471965186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3866017162799835, "target_z": 0.3476562409661323, "ce": 5.700935363769531, "genuineness": 4.545003414154053, "identity": 0.6733057498931885, "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_Infatuation/d1f87db6080ebc3c3bfac94000f1a3ffde3062f9b50e91ecc8e6b4009cf45515.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "5ce99f35d34536b9526ff7b055f6a7dcd51c547b7455289962c063f29db5f65b", "generation_seconds_batch": 18.627726615057327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.24500846862793, "genuineness": 4.406930446624756, "identity": 0.7862546443939209, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "d29fb22ba765340aff266248db359e4137aaeea4d9fbb1550ac1ca399ce63800", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8c3e82cf3f3c0ccd0f47e5b2747c2dad3c984cc22176a5cfe0fc4c779abeb187", "generation_seconds_batch": 32.215818403987214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3950585126876831, "target_z": 0.3632812461283424, "ce": 6.181467056274414, "genuineness": 4.18726921081543, "identity": 0.23705939948558807, "hypothesis": "The 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_Infatuation/d29fb22ba765340aff266248db359e4137aaeea4d9fbb1550ac1ca399ce63800.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": "d2b0ed2c01fd1c40946cda8272d25a2f627df82f7263d87ba915b2cbf9d93c39", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "2167326963e9aacfa6b4f2561c331f7cb23d00c2285c68738f429f01dad07d2a", "generation_seconds_batch": 22.85165358602535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.052558377385139465, "target_z": -0.26953124268686895, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.5520137548446655, "hypothesis": "De sleutels liggen op de keukentafel. Je keek 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_Infatuation/d2b0ed2c01fd1c40946cda8272d25a2f627df82f7263d87ba915b2cbf9d93c39.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "d2b16f5ae2d4f9ad585d9f2b29d5df7473758676fcc434509cb782c8809aff15", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c66212e2b6f8d6d453cc593413236fc58bbcfef41d9580a69a9992b8e5ffddc", "generation_seconds_batch": 17.807832027901895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15906111896038055, "target_z": -0.07275390447549027, "ce": 5.804190158843994, "genuineness": 4.7081804275512695, "identity": 0.6369354724884033, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d2b16f5ae2d4f9ad585d9f2b29d5df7473758676fcc434509cb782c8809aff15.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "d2bffb728d5ee1bc138f5a0ab4c591eef5777fb07daa67a5422bf4e1500f3ce4", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5cb4e6f023cd68853328741156346d7a43f395d4fc91cfd0aff403921ee4a7aa", "generation_seconds_batch": 17.949383190018125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1767675280570984, "target_z": -0.0400390654037432, "ce": 6.205295085906982, "genuineness": 4.6956281661987305, "identity": 0.7441221475601196, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d2bffb728d5ee1bc138f5a0ab4c591eef5777fb07daa67a5422bf4e1500f3ce4.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "d2bffc5ca9c9cab6ff8d5e7835351538a4dd1f8c30b0bf7026ae2352de06336d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46f2bf757906544e30c2abe5a5aba8b7f7960428c1730f8d7870d0a4d0fc3740", "generation_seconds_batch": 17.789703018032014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2893486022949219, "target_z": 0.16796876419607787, "ce": 5.871703147888184, "genuineness": 4.582659721374512, "identity": 0.4202876091003418, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d2bffc5ca9c9cab6ff8d5e7835351538a4dd1f8c30b0bf7026ae2352de06336d.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "d2e7ade71612c7f20fe160c24899a393f25773da1db5e091d9939f300e63ff4a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1fc93ce929477d48012880c95cefe5f5cb1a0a1b67e6cbab8293cc389a4e89d7", "generation_seconds_batch": 25.675912381964736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24072203040122986, "target_z": 0.0781249982792633, "ce": 5.367343425750732, "genuineness": 4.413206577301025, "identity": 0.7344998121261597, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d2e7ade71612c7f20fe160c24899a393f25773da1db5e091d9939f300e63ff4a.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "d31a0eff7753748485bb65f1c44c9fd71237e288c569a454809436ffb6756544", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e84069b67a081219f44023216b0940875c5b2d6e7f0126053b0bf1f61564097f", "generation_seconds_batch": 22.838002366013825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21891936659812927, "target_z": 0.03784180851685931, "ce": 5.550024509429932, "genuineness": 4.306513786315918, "identity": 0.20488056540489197, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d31a0eff7753748485bb65f1c44c9fd71237e288c569a454809436ffb6756544.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "d354321badcfe151ebd8ee64a4ff9919fb74503cf72efb3200b03ae6a365e16d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "69bc1fb9f54f1a6e7a5c922135965b91fa4802044e3d8a97205c756ae093df2a", "generation_seconds_batch": 23.52528971794527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3538316488265991, "target_z": 0.2871093803773022, "ce": 6.006728172302246, "genuineness": 3.823258876800537, "identity": 0.4341365098953247, "hypothesis": "The 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_Infatuation/d354321badcfe151ebd8ee64a4ff9919fb74503cf72efb3200b03ae6a365e16d.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": "d38fb14f050646490b17fadb8c88cf52a901ae1a1498ee5d2641feccc869cf29", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e179905b5667ef3eea6f2989200271a082e450960f70705d5f9976efba7df2db", "generation_seconds_batch": 26.193772151949815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14452600479125977, "target_z": -0.09960937349435538, "ce": 5.8875885009765625, "genuineness": 4.532451152801514, "identity": 0.4620864987373352, "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_Infatuation/d38fb14f050646490b17fadb8c88cf52a901ae1a1498ee5d2641feccc869cf29.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "d3d4beda5e307c06f6d748a01be89022cdd5f61e9e7f774afdb8dd2ce0c8d6fe", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "40b69fb62ae5c413d79f1dabfcae34aa2a9878afa63f6b3d07830af2334e8d99", "generation_seconds_batch": 23.387921464047395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022959589958190918, "target_z": -0.32421876075460443, "ce": 6.229123115539551, "genuineness": 4.319066047668457, "identity": 0.6911634206771851, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d3d4beda5e307c06f6d748a01be89022cdd5f61e9e7f774afdb8dd2ce0c8d6fe.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "909040fb2e035a3b6a011b447f723274e5bf9680f437a6d5621ec1ef068600c0", "generation_seconds_batch": 19.31762018497102, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.023552775382995605, "target_z": -0.4101562616149728, "ce": 6.0146708488464355, "genuineness": 4.65797233581543, "identity": 0.7312735915184021, "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_Infatuation/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "d4bbfc14cd2bda362276cc5bbb9380c8172471a3651a94adf8a38feaf4bb215d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e4a5c0b671473bd37d13a9dd1085db57ef6a72ced2b1de35274fe37bbb0ea7e7", "generation_seconds_batch": 24.174431374995038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05784386396408081, "target_z": -0.25976563510932815, "ce": 6.467403411865234, "genuineness": 4.758388519287109, "identity": 0.6456236839294434, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d4bbfc14cd2bda362276cc5bbb9380c8172471a3651a94adf8a38feaf4bb215d.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "d4c1add5083719f57c82d892d5c7a6d8a8a8054cf425bf4e3213df4c31561b39", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2a31af6b370c676b23619d3340d0c6988225a344cd2bb502245276cecaebe7a", "generation_seconds_batch": 24.363928342005238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007696285843849182, "target_z": -0.38085938381877565, "ce": 6.054384231567383, "genuineness": 4.15588903427124, "identity": 0.538423478603363, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d4c1add5083719f57c82d892d5c7a6d8a8a8054cf425bf4e3213df4c31561b39.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "d4c494f812e6597163f3cd0ee6f9e26ba31490e34fa10fa706b5295f8b648c90", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4f000fd3bfa99e2ffa4432d5256886c67be64f4f415f23aa1e7a8520ed89d298", "generation_seconds_batch": 17.352731473045424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07370036095380783, "target_z": -0.23046874354723734, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.5201230645179749, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d4c494f812e6597163f3cd0ee6f9e26ba31490e34fa10fa706b5295f8b648c90.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "d4d5702fb50c40a0f4d7085b85f5c9f07d20819b64d0761e901370ba87dd5d5e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "76d581aa44cea088ed5fac543ab395313c843cd98c3fe5e40fd47e77c34a8bc3", "generation_seconds_batch": 25.712445350014605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17795675992965698, "target_z": -0.03784180851685931, "ce": 5.911416053771973, "genuineness": 4.607763767242432, "identity": 0.27027586102485657, "hypothesis": "La puerta sigue abierta. he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d4d5702fb50c40a0f4d7085b85f5c9f07d20819b64d0761e901370ba87dd5d5e.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": "d4fdf633aa9e5a998556df54dfab2ebcf76476c7207d0298db0157a0b3f4c8d9", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "0ea51139f5fd030be02685d22b64cb218448ab99e6e83884052cc2dc7c061e4c", "generation_seconds_batch": 20.030469563091174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07951440662145615, "target_z": -0.2197265559396913, "ce": 6.141753673553467, "genuineness": 4.645420074462891, "identity": 0.6170046329498291, "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_Infatuation/d4fdf633aa9e5a998556df54dfab2ebcf76476c7207d0298db0157a0b3f4c8d9.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "d53d50e6cac7ec298b738f0e702d17285f4f102132939a7ffd57508923fa4640", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a1b343f793f0aff24d27a04d102fb7d392ba9b0dd439093e0d885b91eb7494e5", "generation_seconds_batch": 23.557780656032264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13844768702983856, "target_z": -0.11083983735101036, "ce": 6.229123115539551, "genuineness": 4.607763767242432, "identity": 0.6310936212539673, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d53d50e6cac7ec298b738f0e702d17285f4f102132939a7ffd57508923fa4640.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "d556a3dd5fd49be0805a836f44d1e248813440f295f46b834afe6059345f2b65", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "31bacb57e688f61f30fb0092c6688be4e30940daf9fa5dc85f43815cc4e6a1fc", "generation_seconds_batch": 24.493328273994848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27983468770980835, "target_z": 0.15039059897385726, "ce": 5.542081832885742, "genuineness": 4.570107460021973, "identity": 0.7204271554946899, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d556a3dd5fd49be0805a836f44d1e248813440f295f46b834afe6059345f2b65.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": "d5b68377c5498c97ce11ac85cb1d6cda6fc9be5b0cd5a518a66da8b2e7750338", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca786a857a187c0cc418a350efa2b441c2f8cb6083495226bc5c3a3085d543b2", "generation_seconds_batch": 17.458740954985842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1112273782491684, "target_z": -0.16113281411319066, "ce": 6.173524379730225, "genuineness": 4.758388519287109, "identity": 0.785042405128479, "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_Infatuation/d5b68377c5498c97ce11ac85cb1d6cda6fc9be5b0cd5a518a66da8b2e7750338.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "d66e80add6ad7882be9db932f60a6268231eaeba7cc30e8ae652b6e61cda1328", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "38b3601311e2b2aafd7d640d6977c224365fea3d86928991003d4bbf07b64715", "generation_seconds_batch": 25.858876965008676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.007696285843849182, "target_z": -0.38085938381877565, "ce": 6.070269584655762, "genuineness": 4.344170093536377, "identity": 0.38197529315948486, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d66e80add6ad7882be9db932f60a6268231eaeba7cc30e8ae652b6e61cda1328.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "d6f54a637f44bda56d3b1c18438898cf9ede8a9f082293aa1913b5b136dfb3c1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4889afe7dbd663b80a5b6def8bf85a0db34be7726a4c359d9dae373ba76e6ec8", "generation_seconds_batch": 24.765150011051446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21918363869190216, "target_z": 0.03833008476596824, "ce": 6.443574905395508, "genuineness": 4.482243061065674, "identity": 0.3890427052974701, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d6f54a637f44bda56d3b1c18438898cf9ede8a9f082293aa1913b5b136dfb3c1.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "d77ff1794d32df1ed5363f554c7a08cff5b86947bf00b46a6b07fd04c7cfc722", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f73e4bf4d1f727ec56c8aee92f0bb4f13a48921a4d7c6340435cd2b3ff5394f1", "generation_seconds_batch": 24.782790525001474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14294035732746124, "target_z": -0.10253905852079635, "ce": 6.1894097328186035, "genuineness": 4.3881025314331055, "identity": 0.351418673992157, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d77ff1794d32df1ed5363f554c7a08cff5b86947bf00b46a6b07fd04c7cfc722.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "d7ba48fc637905c882e2c5f443935a99b335b732667127bcf569a2381dacf0cf", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "609d49b3937f34a9450a7bf998c20da16b55a3f3326e58ac5f34f18ca4641974", "generation_seconds_batch": 25.661776268971153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6825894713401794, "target_z": 0.894531201389188, "ce": 5.704906940460205, "genuineness": 4.65797233581543, "identity": 0.723778486251831, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d7ba48fc637905c882e2c5f443935a99b335b732667127bcf569a2381dacf0cf.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "d8aefd9d1773e50f001cd2fab8b12b30c276835f0ed9630cf90d98ae5e97e005", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e8971f119bd03a462c8a281bf674fbe323104fba0cd8573e35bf1841af254973", "generation_seconds_batch": 24.708613186026923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06101517379283905, "target_z": -0.25390623752465885, "ce": 6.054384231567383, "genuineness": 4.570107460021973, "identity": 0.5174458622932434, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d8aefd9d1773e50f001cd2fab8b12b30c276835f0ed9630cf90d98ae5e97e005.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": "d8e61725fb958d35849a803c9fcbd4037e4e740e4035e4ee0d4b096c029834ad", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1933e5d3a2e1b7073bfff16bbc815ee2732c927d58c414b57f5a06d9c8f9cf3", "generation_seconds_batch": 17.490969715057872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08955684304237366, "target_z": -0.20117187951693385, "ce": 6.340320587158203, "genuineness": 4.457139015197754, "identity": 0.19670309126377106, "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_Infatuation/d8e61725fb958d35849a803c9fcbd4037e4e740e4035e4ee0d4b096c029834ad.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": "d9547925295928b20d9c85f4881f0d25f51f0ed87ea1d12443ddeced86455ff4", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2bb493d2a480c5f2a14f20f088f6b3f6495410854494ef63db6eaccbeb976cd0", "generation_seconds_batch": 17.182931135059334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07898585498332977, "target_z": -0.22070312220380284, "ce": 6.078212261199951, "genuineness": 4.68307638168335, "identity": 0.5195738673210144, "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_Infatuation/d9547925295928b20d9c85f4881f0d25f51f0ed87ea1d12443ddeced86455ff4.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "d9b64f9a1be0683dd3a5af9456f44e262473397422ef33fe2ddd9015949cdae8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7e58f1cb32fadc6471d6e92b5fb69acfeb1b426ddaa586a5d1e90ab057c598bc", "generation_seconds_batch": 26.16281892999541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11175592988729477, "target_z": -0.16015624784907911, "ce": 5.855817794799805, "genuineness": 4.68307638168335, "identity": 0.6657124757766724, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/d9b64f9a1be0683dd3a5af9456f44e262473397422ef33fe2ddd9015949cdae8.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "da0c5a4c4c81a5c6f37220cd22422b8a495d817e0b88753bdbf15032e812f45f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c09470136c291ab6b6140b5f0ce04b5f5e793e20f2b12b2f9c815be05e4f03e8", "generation_seconds_batch": 24.119457418099046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.047272875905036926, "target_z": -0.27929687779619716, "ce": 6.0305562019348145, "genuineness": 4.18726921081543, "identity": 0.32634860277175903, "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_Infatuation/da0c5a4c4c81a5c6f37220cd22422b8a495d817e0b88753bdbf15032e812f45f.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "da33b66bc94e25414e6f3c5c2e27ed8096575d4bcfa167a29c03354112c70d3e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "870ea07bc7b4966b5660a8748093cb07e344025e2ab4d0528b407120467838fa", "generation_seconds_batch": 17.748936638003215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9764630794525146, "target_z": 1.4375000068829469, "ce": 5.792276382446289, "genuineness": 4.519899368286133, "identity": 0.6568691730499268, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/da33b66bc94e25414e6f3c5c2e27ed8096575d4bcfa167a29c03354112c70d3e.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "daa3b0a07d23f92cb43b95168bb80a2410c14b62a35499a75ad2e857abfc4f60", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b6fdb821e97192688be580691fcb799b1be0b5b1d0b0d23504b0e4a67829825a", "generation_seconds_batch": 23.350679737050086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09589944034814835, "target_z": -0.18945312564527628, "ce": 6.308549880981445, "genuineness": 4.20609712600708, "identity": 0.39768922328948975, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/daa3b0a07d23f92cb43b95168bb80a2410c14b62a35499a75ad2e857abfc4f60.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "dad6cf430879b112b371bf9bc20664f993f3512c199d619165d4ad5edba28664", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c151f7e0d1481bc77089423aef52129a1f60bc286ea767b5c9bb78c8e10013de", "generation_seconds_batch": 25.724155250936747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03881607949733734, "target_z": -0.29492188295840727, "ce": 6.2767791748046875, "genuineness": 4.532451152801514, "identity": 0.7157531380653381, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/dad6cf430879b112b371bf9bc20664f993f3512c199d619165d4ad5edba28664.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "eaf26ea39ec8190b6c5e71216b2dca4c803b00fc07ca5b40bb31d97494acea9f", "generation_seconds_batch": 17.124287017970346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011331498622894287, "target_z": -0.34570313596969654, "ce": 6.41180419921875, "genuineness": 4.105680465698242, "identity": 0.3776978850364685, "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_Infatuation/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "db6d3a548f7cc31a51057566ba1ba71464787c2c22e0f46ad467d4053c4274a0", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cf73b9779db1a32f8fdec0fe80ca48e452d57b7f2879d16332f07f6a64892a01", "generation_seconds_batch": 25.377681910060346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38025912642478943, "target_z": 0.33593750086036833, "ce": 6.0305562019348145, "genuineness": 4.6203155517578125, "identity": 0.7741720080375671, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/db6d3a548f7cc31a51057566ba1ba71464787c2c22e0f46ad467d4053c4274a0.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "db7358bdee61811d0720b8d9bf8d95f9ba1958ecaefbe6e5206d75829547ad96", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "98a5e25104c118ac6ad0ca47e4fe1e7acb91f9d19ba19c3c0b7668f6c4ab5718", "generation_seconds_batch": 27.235756952897646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2560499608516693, "target_z": 0.1064452960454552, "ce": 5.967014789581299, "genuineness": 3.8546390533447266, "identity": 0.3568788766860962, "hypothesis": "The 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_Infatuation/db7358bdee61811d0720b8d9bf8d95f9ba1958ecaefbe6e5206d75829547ad96.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "dc1922bdbeb95461df01ee1c5114c7de973f4c39032906abb98e68bf5033e159", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0d01f6f85f2004a1967471a91ce68e92d2dbcfe0f9fc8dcee2c7bd4922e79d3e", "generation_seconds_batch": 28.504754918045364, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8326975703239441, "target_z": 1.1718749741889494, "ce": 5.708878040313721, "genuineness": 4.607763767242432, "identity": 0.7941492795944214, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/dc1922bdbeb95461df01ee1c5114c7de973f4c39032906abb98e68bf5033e159.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "dc343f0f183b06741ac9079aca9a8597f2a4a4d5c5f37bc52c9f2e3418923f94", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d71711967e26c306bd36b0a6ee76bab4f2e4d860b9c8dc786927ec6807b9e9ed", "generation_seconds_batch": 25.76860762492288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07370036095380783, "target_z": -0.23046874354723734, "ce": 5.442798614501953, "genuineness": 4.381826400756836, "identity": 0.2857479453086853, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/dc343f0f183b06741ac9079aca9a8597f2a4a4d5c5f37bc52c9f2e3418923f94.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "dc5cc25983be65b23b7d7869f88f0d1b0d62bb8193dc766bf043171b41586452", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cccd44732fd1ea26f680eec33f9cfae5564649bd077602c1ad4cbc1e4d55ea3c", "generation_seconds_batch": 24.373071242007427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35277456045150757, "target_z": 0.28515627538086646, "ce": 5.530168056488037, "genuineness": 4.049196243286133, "identity": 0.5712049603462219, "hypothesis": "Ik heb het klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/dc5cc25983be65b23b7d7869f88f0d1b0d62bb8193dc766bf043171b41586452.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "dcb47752abaa2d9b147380ff3350c6b6f55abde9950b9b30aa9a51625c82b736", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7f5020ba6a3f20d929faa2331375223b50569f33c6e0827baf02cada3b236997", "generation_seconds_batch": 31.104960650089197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.002874717116355896, "target_z": -0.3613281136001193, "ce": 5.669164657592773, "genuineness": 4.293961524963379, "identity": 0.49342256784439087, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/dcb47752abaa2d9b147380ff3350c6b6f55abde9950b9b30aa9a51625c82b736.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "dde58cb2262b329a0ac1e5dcdb36c5f96be2bf430e0c7369f2cf61169899bee2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a958fd64e51436981cd7369a497eeecc5d5ba2c86d13ff2987c00082cbc3523a", "generation_seconds_batch": 18.263117972994223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14690446853637695, "target_z": -0.0952148597205876, "ce": 6.395919322967529, "genuineness": 4.507347106933594, "identity": 0.4000132083892822, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/dde58cb2262b329a0ac1e5dcdb36c5f96be2bf430e0c7369f2cf61169899bee2.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": "dded9e9219b70e45f1f96f0fef464fca9c0cea8be30da6c3b47b7aaeaa691d96", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e102eaa5b251bad9804f4dc47574a53032b67b99b427d930174edc8fb89c9b54", "generation_seconds_batch": 16.630369925056584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033530592918395996, "target_z": -0.30468749053594807, "ce": 5.208489894866943, "genuineness": 3.998987913131714, "identity": 0.372299462556839, "hypothesis": "De sleutels liggen op de keukentafel. De cake in de la. En daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/dded9e9219b70e45f1f96f0fef464fca9c0cea8be30da6c3b47b7aaeaa691d96.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "de2c46e9667949fc488959342f8ecf2275c647ff6e2a0d56cc91257d9dbd971e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8ad0d54fe80b8dd78d52e9998ef79102a116e57307e4b5302f85843e8b6184c5", "generation_seconds_batch": 26.215454565011896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09219959378242493, "target_z": -0.19628906196226978, "ce": 5.919358730316162, "genuineness": 4.532451152801514, "identity": 0.38618290424346924, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/de2c46e9667949fc488959342f8ecf2275c647ff6e2a0d56cc91257d9dbd971e.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": "debddc4683b1959e606beebce71c0aafc41e48a400be82dcd9dfd139b3ee87a5", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f570931f6f84e94572736d14cb361fd15877947b3bd0ec384b55189c3eb59d9f", "generation_seconds_batch": 16.597423230996355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008753374218940735, "target_z": -0.3828124888152114, "ce": 5.95112943649292, "genuineness": 4.406930446624756, "identity": 0.7122475504875183, "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_Infatuation/debddc4683b1959e606beebce71c0aafc41e48a400be82dcd9dfd139b3ee87a5.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "def143f5deafff59252d0f101785d9c46c48d8a9c3e1c0a77e874d5b0fc73a9b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5e187b7afa0f524f589c2783cc679cb047a19e3d97c5377d1164ce2488488e1a", "generation_seconds_batch": 25.832880217931233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1297266185283661, "target_z": -0.12695311876232943, "ce": 4.867948055267334, "genuineness": 4.137060642242432, "identity": 0.35971322655677795, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla, dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/def143f5deafff59252d0f101785d9c46c48d8a9c3e1c0a77e874d5b0fc73a9b.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "df0746e415b8a5879304380743709b04a03be5da271cffb71374e7400c7aff55", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c33a633c9c822e83203ecd3efeb457d5ae234b8ce212d6a7f990f613bf16804f", "generation_seconds_batch": 24.474192184978165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 5.530168056488037, "genuineness": 4.469690799713135, "identity": 0.3598478436470032, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/df0746e415b8a5879304380743709b04a03be5da271cffb71374e7400c7aff55.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "df39e220eccd89f657fdda37d9aaa7d2f9528ff0921361527fd6eb936a0297dc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7b8b20e1bc9995078b7ef3f1369f620ba7ee26f7c46995956fd34d5302efb1fa", "generation_seconds_batch": 23.68701149302069, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02507379651069641, "target_z": -0.32031249569815823, "ce": 6.348263263702393, "genuineness": 4.400654315948486, "identity": 0.6876497268676758, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/df39e220eccd89f657fdda37d9aaa7d2f9528ff0921361527fd6eb936a0297dc.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "dfebe299ae776ed52a807ed33247a65484c0f95e58b5a3c0046ead424acfef83", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "51122690a4cf2c6013b8bf423546ab5277d538a4e722aba89e109b2dc8098294", "generation_seconds_batch": 23.873147011967376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01509597897529602, "target_z": -0.39453125645276266, "ce": 6.252951145172119, "genuineness": 4.331617832183838, "identity": 0.5075427889823914, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/dfebe299ae776ed52a807ed33247a65484c0f95e58b5a3c0046ead424acfef83.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "e0208f01aae4bdee1ad3bf893ea0caa9d06dc0759c3a0f66cd7bd164421675d1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3d699f4c7ce21d44d888a81945549d12a146a3e461b7440f6699e3629e229edc", "generation_seconds_batch": 25.307325784000568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10224203765392303, "target_z": -0.17773437177361867, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.7511855363845825, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e0208f01aae4bdee1ad3bf893ea0caa9d06dc0759c3a0f66cd7bd164421675d1.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "e03d61e6b4b7c3e18f0c144351c5297fcfbe32a1b265752894389b60ddd3d664", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f54c7403613b9cae1872f942ef4aff75a2925b8ff920aaeadf73f9ffcfc5bbfe", "generation_seconds_batch": 17.352731473045424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.008753374218940735, "target_z": -0.3828124888152114, "ce": 6.0305562019348145, "genuineness": 4.469690799713135, "identity": 0.5539423227310181, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e03d61e6b4b7c3e18f0c144351c5297fcfbe32a1b265752894389b60ddd3d664.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "e063536d1e13014ac0acee1a8916e3b7ca5471eba5df609eb8565a37f4db983c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4843e3b32ee98305c3343cfadceb2f8c85b6b98d8e2766f82693ea18d384915e", "generation_seconds_batch": 16.929180564940907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17187844216823578, "target_z": -0.04907227237351429, "ce": 5.33954381942749, "genuineness": 4.18099308013916, "identity": 0.3513759970664978, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e063536d1e13014ac0acee1a8916e3b7ca5471eba5df609eb8565a37f4db983c.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "e08820158b398d8037ef984a20b56c36b3f2ca0990eb599d9a4e194d2db0c044", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1c7ffa400a40c1a3c3b8b949aa29b8320bc9de0d92ef530856cb526ff1d7f3fa", "generation_seconds_batch": 26.043136209016666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.010274410247802734, "target_z": -0.3476562409661323, "ce": 6.157639026641846, "genuineness": 4.419482707977295, "identity": 0.5357593894004822, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e08820158b398d8037ef984a20b56c36b3f2ca0990eb599d9a4e194d2db0c044.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": "e09c24b69070a2236a1ec998a1954d23261b25a70cd560c6d7e1c7e804362963", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c34b0c62dc43366a87ad91928efc627370858c527e502e3fae4684db87fa0c6", "generation_seconds_batch": 26.169258885085583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13289791345596313, "target_z": -0.12109374870944746, "ce": 5.824047088623047, "genuineness": 4.406930446624756, "identity": 0.5387191772460938, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e09c24b69070a2236a1ec998a1954d23261b25a70cd560c6d7e1c7e804362963.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "e0bc771bde66937aa2ab6e39a58265d10effcbfd30ad6b768bf0cf9f570aa85c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5052adff35b1dc198e974623da423bcc339f7c138eceaef4b2f52a3872302c2e", "generation_seconds_batch": 17.286090894951485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07158616185188293, "target_z": -0.23437499483778987, "ce": 5.514282703399658, "genuineness": 4.519899368286133, "identity": 0.3522312641143799, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e0bc771bde66937aa2ab6e39a58265d10effcbfd30ad6b768bf0cf9f570aa85c.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "e114f9af4a199d34c19e8d748763be92a9a105c910221285a192d5a14ce5992d", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fd7efbbe6334f651dd718ec193f7480ecae2fb53b93684229d66ae4995dcb249", "generation_seconds_batch": 24.815585158998147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.058437034487724304, "target_z": -0.4746093597284617, "ce": 6.046441555023193, "genuineness": 4.432034492492676, "identity": 0.5921974182128906, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e114f9af4a199d34c19e8d748763be92a9a105c910221285a192d5a14ce5992d.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": "e1168cbf2adda619b8fdd1f3e95aa69dcb64bef919572520f5bdb575b8c22379", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "30a292821086987416461b3027eab0d0b3bd596575a87f4cb1d0ae421f06ed64", "generation_seconds_batch": 18.310121631016955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0018176138401031494, "target_z": -0.3632812461283424, "ce": 6.165581703186035, "genuineness": 4.545003414154053, "identity": 0.4997648596763611, "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_Infatuation/e1168cbf2adda619b8fdd1f3e95aa69dcb64bef919572520f5bdb575b8c22379.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "e1fccdf8fb53db641ae7182517fb46cd522a18b4371b706285c5252c9bc85c82", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dec740992023eeffd61226bd898805778f2632dd6483f2374183b54dd1e0f5a8", "generation_seconds_batch": 17.129387527005747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06735776364803314, "target_z": -0.24218749741889492, "ce": 6.1020402908325195, "genuineness": 4.532451152801514, "identity": 0.5085947513580322, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e1fccdf8fb53db641ae7182517fb46cd522a18b4371b706285c5252c9bc85c82.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "e245403fe71d08a4f1c65bc92052376cfb304b40cca50872221b553b8bb7535e", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3cd3db0517cae266aadf869d0fd0468ff3cba900652b6f9a04a6e169017534c6", "generation_seconds_batch": 18.245072123012505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03306666016578674, "target_z": -0.42773437177361867, "ce": 6.1894097328186035, "genuineness": 4.3127899169921875, "identity": 0.6114048957824707, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e245403fe71d08a4f1c65bc92052376cfb304b40cca50872221b553b8bb7535e.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "e26e935e6a580add5f63012767132644e447e23e6e12ab5e48e72060440788fa", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ce00af2ac231ab53e7016452507e91e7bfb89a4c9fc39b7460164e92ef8839be", "generation_seconds_batch": 24.62782061996404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5705369710922241, "target_z": 0.6874999793511595, "ce": 5.677107334136963, "genuineness": 4.344170093536377, "identity": 0.8164548873901367, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e26e935e6a580add5f63012767132644e447e23e6e12ab5e48e72060440788fa.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "e26ecf3ca79c1614b04c5b61c98847e0370ddd37952eaea858b3584af1238af8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dde5b7da38141c2af942bc256f6965f5737899b72108f54d2c97c6a6817e7dca", "generation_seconds_batch": 22.858118447940797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25763562321662903, "target_z": 0.10937500860368356, "ce": 6.046441555023193, "genuineness": 4.607763767242432, "identity": 0.6131031513214111, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e26ecf3ca79c1614b04c5b61c98847e0370ddd37952eaea858b3584af1238af8.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "e28b7b94ca326c621536f11233690229567696a03265e82b20f40408098779a3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2361e30dd2648f53c61afa80a7dc4cdc0f24f603a3d72b1dd6d498a7e81ee282", "generation_seconds_batch": 17.36083770892583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07370036095380783, "target_z": -0.23046874354723734, "ce": 5.780362129211426, "genuineness": 4.293961524963379, "identity": 0.566685676574707, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e28b7b94ca326c621536f11233690229567696a03265e82b20f40408098779a3.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "e3154112e1f9926c715bdac7b74e9221d9b3a239c4597781dbf6841dc11c7e41", "bucket": "emo_Infatuation", "phase": "wording", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a92754ae31ab6e9ec804801602c7dbe145590f532ba0344abcdc779111116b90", "generation_seconds_batch": 18.245072123012505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03881607949733734, "target_z": -0.29492188295840727, "ce": 5.847874641418457, "genuineness": 4.3127899169921875, "identity": 0.5559566020965576, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e3154112e1f9926c715bdac7b74e9221d9b3a239c4597781dbf6841dc11c7e41.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "e31980313fa19587c71dd23fe2b0b3324d9a6e4e93c8904cc91142a1eb7f1f01", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4bbabfb52972603bf24379ba7e5e07df1f0bf938912df4baf60afa023fdd920b", "generation_seconds_batch": 24.363928342005238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018731191754341125, "target_z": -0.33203126333570954, "ce": 6.332377910614014, "genuineness": 4.595211505889893, "identity": 0.7101973295211792, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e31980313fa19587c71dd23fe2b0b3324d9a6e4e93c8904cc91142a1eb7f1f01.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": "e351da1b836fcd4cef37ff98ba82d56609d8984eddeb623e200ff57ab4e6f962", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "506897494ecd05013f43615969c49d1943543f166b2ba0a189e853c64e62ca19", "generation_seconds_batch": 19.158219364006072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12655532360076904, "target_z": -0.13281248881521138, "ce": 6.24500846862793, "genuineness": 4.6956281661987305, "identity": 0.6583638191223145, "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_Infatuation/e351da1b836fcd4cef37ff98ba82d56609d8984eddeb623e200ff57ab4e6f962.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "e3aad093d0fb1ca9fe2a08fae752be67f34a7bbfdfb1d6252062d4b2e282bdcb", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78452c65da8557420dcafe6686c2f305470687b53986652ac94996f7c3f3d4dd", "generation_seconds_batch": 22.940151832066476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1673857718706131, "target_z": -0.057373051203728286, "ce": 5.71682071685791, "genuineness": 4.545003414154053, "identity": 0.21261653304100037, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e3aad093d0fb1ca9fe2a08fae752be67f34a7bbfdfb1d6252062d4b2e282bdcb.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": "e3af050015e7ddca2827d23b92b1f11e66301ab3611d3523218a74e17f94335c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "e95c68b7be2e8ca5583570157aa68c1dc413e98e49aee64f60efda4028c2ff68", "generation_seconds_batch": 22.651297904085368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.03835216164588928, "target_z": -0.4375000068829468, "ce": 6.300607204437256, "genuineness": 4.281409740447998, "identity": 0.5888442993164062, "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_Infatuation/e3af050015e7ddca2827d23b92b1f11e66301ab3611d3523218a74e17f94335c.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "e3d55bf13b4153a5005de04aff724975d638d83416e2e3a8f4a3b156d4341d86", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dccc0d25410388ad8506fffffb8f90cc0f5e710a586349340d864c2680b70cb2", "generation_seconds_batch": 18.47185286693275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12708386778831482, "target_z": -0.1318359363169935, "ce": 6.062326908111572, "genuineness": 4.068024158477783, "identity": 0.3174675703048706, "hypothesis": "The 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_Infatuation/e3d55bf13b4153a5005de04aff724975d638d83416e2e3a8f4a3b156d4341d86.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "e4247b65ca767b3bc7407ebfd77c067fb71724f310451f06126804b63edc085f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b5604f304ffe40a1c8ef4416f6cdfd88a978c3622beef94d8efe6523f08a31f9", "generation_seconds_batch": 24.172994106076658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07370036095380783, "target_z": -0.23046874354723734, "ce": 6.1020402908325195, "genuineness": 4.6956281661987305, "identity": 0.7738050222396851, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e4247b65ca767b3bc7407ebfd77c067fb71724f310451f06126804b63edc085f.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "e4a70fbad61b58f904e99cbd68524e4e81a29fd3bff355a74ba6c3c1b8d8fb72", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3eecbd4d00651670af115df759390c96bb7e41b927bff3873de230c30b9d3aec", "generation_seconds_batch": 23.945550378062762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.029302194714546204, "target_z": -0.3124999931170532, "ce": 6.133810997009277, "genuineness": 4.482243061065674, "identity": 0.5334073305130005, "hypothesis": "La puerta sigue abierta. He dicho un seno aún, though. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.4666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e4a70fbad61b58f904e99cbd68524e4e81a29fd3bff355a74ba6c3c1b8d8fb72.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "e512fcbb0c215d40c1ef1cc91b12d4238404e740fe3d11a5a542d7bcf8fca664", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "76c36edf59e951af4d919110f5a358c66b2c0b0a9dca684d34f09578ecb08041", "generation_seconds_batch": 23.1568539889995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1580040156841278, "target_z": -0.07470703700371338, "ce": 5.736677646636963, "genuineness": 4.582659721374512, "identity": 0.7561339139938354, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e512fcbb0c215d40c1ef1cc91b12d4238404e740fe3d11a5a542d7bcf8fca664.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "e51e75276a48e4273637b3614f4583314b6685b84174ed8d16aebf630be2ba9f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8429fe7f4497ea57731c189ae21826fba4af8904042305cb408cba2b2a821b67", "generation_seconds_batch": 19.48157295002602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46165573596954346, "target_z": 0.48632807230243824, "ce": 6.213237762451172, "genuineness": 4.337893962860107, "identity": 0.3649196922779083, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e51e75276a48e4273637b3614f4583314b6685b84174ed8d16aebf630be2ba9f.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "e541593946052885bc3f82b1cbae5c79df2c9b39835ef1514aca5d34d1b0a26b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "07f5c694e39ee77eca365b33103c7bc342ec325c8145fd5431868cb3e8b0498c", "generation_seconds_batch": 26.867222398053855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4690554738044739, "target_z": 0.5000000275317874, "ce": 5.95112943649292, "genuineness": 4.162164688110352, "identity": 0.36459994316101074, "hypothesis": "The 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_Infatuation/e541593946052885bc3f82b1cbae5c79df2c9b39835ef1514aca5d34d1b0a26b.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "e54dd03bd4682e2f7ffb7db5ccd3302be05b71b0ef1c714872469658c0825669", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1aec6dbc08d808df849fc3c008ce522e2353a428b4074ae8b71ccd959baf6852", "generation_seconds_batch": 23.33234053198248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03670188784599304, "target_z": -0.2988281204830661, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.7384088039398193, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e54dd03bd4682e2f7ffb7db5ccd3302be05b71b0ef1c714872469658c0825669.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "e5a2d3dcafdf0b0cfbbbfcf061d10003ce19138574a20d175ffcc902b4bf6efc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "87ad8ed54cf9fbd5c6a4b4aa2116ff552695ba1eed139dee0aab1bdfab14e5ce", "generation_seconds_batch": 25.16330684896093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08215714991092682, "target_z": -0.21484375215092089, "ce": 5.871703147888184, "genuineness": 4.482243061065674, "identity": 0.4282558560371399, "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_Infatuation/e5a2d3dcafdf0b0cfbbbfcf061d10003ce19138574a20d175ffcc902b4bf6efc.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": "e5e4ad75bed449f5710fa5b62749ac4eab14f643526fae6332ba65a50926ec95", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1786dc948dd5a597d5ef820051574ffd635afd64332ebba4b477b12f82ed6cc", "generation_seconds_batch": 23.55714846297633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006046012043952942, "target_z": -0.35546874354723734, "ce": 5.597680568695068, "genuineness": 4.394378662109375, "identity": 0.7922860383987427, "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_Infatuation/e5e4ad75bed449f5710fa5b62749ac4eab14f643526fae6332ba65a50926ec95.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "e5fac8cb4f3f3785920878bb4f00d21cefe85afc26eb123fc60a74cad50975bd", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "310be0fdbf86ede94e4bae3db2db161781f0d60b790ebe9e057aae30181e5b24", "generation_seconds_batch": 25.239816828048788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 5.95112943649292, "genuineness": 4.344170093536377, "identity": 0.5029513835906982, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e5fac8cb4f3f3785920878bb4f00d21cefe85afc26eb123fc60a74cad50975bd.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "e667b15e9d283e61711fe809a012588ec1f911cce664a35ad9c98eb6f0003cdd", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "65d9c5ad1410385ce06cdf943246f9ea6f3aea503064aa6420237bc43c9e82c0", "generation_seconds_batch": 24.76711841498036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14743302762508392, "target_z": -0.09423827969058235, "ce": 5.25614595413208, "genuineness": 4.494794845581055, "identity": 0.4619747996330261, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e667b15e9d283e61711fe809a012588ec1f911cce664a35ad9c98eb6f0003cdd.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "e6c3ae40eb4b8a30006ee73ea3468055cf1e93a5240cddeb961608a7b212ac0a", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ffc0303f58d2940e65fa9da6ce3324c957e9a9f6cc137f07fb641ab3d6b7bc9c", "generation_seconds_batch": 26.164717542007565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.471169650554657, "target_z": 0.5039062375246588, "ce": 5.689021587371826, "genuineness": 4.344170093536377, "identity": 0.4565560221672058, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e6c3ae40eb4b8a30006ee73ea3468055cf1e93a5240cddeb961608a7b212ac0a.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "03fce8d8af34dff64fb6e84e9ace9c17a38cafa0e3ea7b087e5f4af5fd18b8be", "generation_seconds_batch": 19.495055604027584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10224203765392303, "target_z": -0.17773437177361867, "ce": 6.475345611572266, "genuineness": 4.394378662109375, "identity": 0.382091224193573, "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "e6fe5104dda7136bab5b711b80be40f7bb511c76bc8091f8aed5141d431d770c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9ced095b583ac7796e18fc26c461bb81b9da2ed8453ae48f0d3b5314b152580b", "generation_seconds_batch": 17.43683027906809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.010867580771446228, "target_z": -0.3867187538716576, "ce": 6.348263263702393, "genuineness": 4.419482707977295, "identity": 0.4501132667064667, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e6fe5104dda7136bab5b711b80be40f7bb511c76bc8091f8aed5141d431d770c.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "e70801a94647f09472c4983f14abe59e86f57fdbab5bf41cb4edb566a4483722", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "47b0597dfd4eae903233d8254c1290a4a8fa83360ea8d5956e724241def9c870", "generation_seconds_batch": 27.514330678037368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3200044631958008, "target_z": 0.2246093597284617, "ce": 5.665193557739258, "genuineness": 4.519899368286133, "identity": 0.5702677965164185, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e70801a94647f09472c4983f14abe59e86f57fdbab5bf41cb4edb566a4483722.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": "e72716f595f20afbb5e832dc2b5594013945e73f2c2c8fcf905bf22a0d5623c5", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bf74146e5df278789fd754e316250602bf21ec721e7a015b6d896a5abf6babdd", "generation_seconds_batch": 24.01210499694571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21343566477298737, "target_z": 0.027709973103646278, "ce": 6.09409761428833, "genuineness": 4.331617832183838, "identity": 0.5351788997650146, "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_Infatuation/e72716f595f20afbb5e832dc2b5594013945e73f2c2c8fcf905bf22a0d5623c5.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "e78116b0408a307b7b74799b0fa3bf5fc5e6b402d4b2f26f36ecc2f58e95fd43", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4f30da879b49ee5369adb89e7afad4120f8aed1bc6c775f0f868e95794001940", "generation_seconds_batch": 25.055259536020458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41831469535827637, "target_z": 0.40624999655852656, "ce": 5.736677646636963, "genuineness": 4.21237325668335, "identity": 0.280204713344574, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e78116b0408a307b7b74799b0fa3bf5fc5e6b402d4b2f26f36ecc2f58e95fd43.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "e7827fe3c7cc7b3c400a22f1ec46e1a6fc158dec0ee60cac92691712156e1f37", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b66f018ac2875bf2e72d9769965110e272c356b7629d96b937454a3652dcfc60", "generation_seconds_batch": 26.381115291966125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6762468814849854, "target_z": 0.882812461283424, "ce": 5.927301406860352, "genuineness": 4.381826400756836, "identity": 0.4160444736480713, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e7827fe3c7cc7b3c400a22f1ec46e1a6fc158dec0ee60cac92691712156e1f37.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "e7e9a1a1851733d2d7927684db7b97bfd1cac93a55d3a2035b354b893c84d6c3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7bb0a867d9e39c97d10176bde10ad72b4927f7ae7a937bf63d70e7856d0a7761", "generation_seconds_batch": 25.687962163006887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022959589958190918, "target_z": -0.32421876075460443, "ce": 6.284721851348877, "genuineness": 4.68307638168335, "identity": 0.38540971279144287, "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_Infatuation/e7e9a1a1851733d2d7927684db7b97bfd1cac93a55d3a2035b354b893c84d6c3.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "e8559dc8d6e2db1d3ef2d5a6b38a2bfb8bbf2b5aac38a4f13337a23b2f8cb11f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e5bae4be755593bce749cd50578845c01bbf27273e467c6e9a99e4a9714b2c95", "generation_seconds_batch": 18.304584442987107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08215714991092682, "target_z": -0.21484375215092089, "ce": 6.046441555023193, "genuineness": 4.68307638168335, "identity": 0.7949644923210144, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e8559dc8d6e2db1d3ef2d5a6b38a2bfb8bbf2b5aac38a4f13337a23b2f8cb11f.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "e8d7ba5cf75e43f16404c2b9a7fc1677cc672535ea20bf7e0c354e11705cded1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "59f64594e320323e5bafc059d7830cf0723534f4391415db37e5190efcec117b", "generation_seconds_batch": 23.46867728396319, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09378524124622345, "target_z": -0.1933593769358288, "ce": 5.752562999725342, "genuineness": 4.432034492492676, "identity": 0.26528072357177734, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e8d7ba5cf75e43f16404c2b9a7fc1677cc672535ea20bf7e0c354e11705cded1.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "e922220b6f735007432a5450b41ddd0aee4bf4c732e299270b8cd944bc6d3256", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8990f3586d955ae6ce41fda70c1f165fc3915f41352b9c1c8ebb837d8005e04e", "generation_seconds_batch": 17.310886939056218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3548887372016907, "target_z": 0.28906248537373797, "ce": 5.363371849060059, "genuineness": 4.055472373962402, "identity": 0.3344954252243042, "hypothesis": "The 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_Infatuation/e922220b6f735007432a5450b41ddd0aee4bf4c732e299270b8cd944bc6d3256.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "e9d15f2d9d9fa564ae6747585d480baa59b6050346d3b7bcd03cb1aeb1bc9d45", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dfbc6817aaa1744816f0980f012ac9d2f68f86caae8657725de8a56714620f98", "generation_seconds_batch": 19.334795356029645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43734246492385864, "target_z": 0.4414062168758183, "ce": 5.7684478759765625, "genuineness": 4.6705241203308105, "identity": 0.8785445690155029, "hypothesis": "La porte 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_Infatuation/e9d15f2d9d9fa564ae6747585d480baa59b6050346d3b7bcd03cb1aeb1bc9d45.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "abe6724af3bb20d219fc9072ad204699b341acb99d73fdc6ab6854823c746121", "generation_seconds_batch": 18.079500308958814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03458768129348755, "target_z": -0.3027343855395124, "ce": 6.356205940246582, "genuineness": 4.444586753845215, "identity": 0.45063918828964233, "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_Infatuation/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "e9f06827097605ea08686b395b1ec383b39681c51594c82514dc8e91f587e919", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0d3c93f456124cc9f1369e8dd7372b8ad70f36b5bf6b8dc8f9b179311b3f84e9", "generation_seconds_batch": 25.660001867916435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.025666967034339905, "target_z": -0.41406249913963167, "ce": 6.24500846862793, "genuineness": 4.394378662109375, "identity": 0.6120871305465698, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/e9f06827097605ea08686b395b1ec383b39681c51594c82514dc8e91f587e919.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "ea0ae5862a4003e4a4db63aec22dcb222d948171155f41220769acaefc4a421e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e2828430e9550510b0215159587eb1366b3839676912a8ce3e4d5e660e98e764", "generation_seconds_batch": 25.372966546099633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.65510493516922, "target_z": 0.8437500309732608, "ce": 5.780362129211426, "genuineness": 3.8922953605651855, "identity": 0.44648849964141846, "hypothesis": "The 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_Infatuation/ea0ae5862a4003e4a4db63aec22dcb222d948171155f41220769acaefc4a421e.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": "ea3255af0333b266740d95f30f96361765a4dd53e1da62cbcb9446c574f26d30", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f6fe2f25c9fe717bdae218507681b56966de176cec822169161b45d73c669ba5", "generation_seconds_batch": 16.699276280007325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1291980743408203, "target_z": -0.1279296712605473, "ce": 6.125868320465088, "genuineness": 4.432034492492676, "identity": 0.4750235676765442, "hypothesis": "Je bericht kwam nadat ik vertrokken was, ik las het twee keer en legde mijn telefoon weg. Zag maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ea3255af0333b266740d95f30f96361765a4dd53e1da62cbcb9446c574f26d30.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": "ea4aaa4834e1b0b0b2e36ad95db40c7c56c3d1b350b2d2eae5a63b5d32ff7c66", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67d37934d14d35afd832a189cfd3552b524d45f8e22a38e969afa68cf73e248f", "generation_seconds_batch": 23.410479686921462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07792875170707703, "target_z": -0.22265625473202597, "ce": 5.879645347595215, "genuineness": 4.381826400756836, "identity": 0.2506740093231201, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de laag en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ea4aaa4834e1b0b0b2e36ad95db40c7c56c3d1b350b2d2eae5a63b5d32ff7c66.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "ea8ae5dce15f1dded5ea4ed0ad13d907d9e021a566b24c4ca822f6bf5b4531af", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2478248e845ae1b30fcd12068df1dfbcd04c0216529fa296df130fd87f6b7cd5", "generation_seconds_batch": 24.527209465042688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5049968361854553, "target_z": 0.5664062581734993, "ce": 5.272031307220459, "genuineness": 4.758388519287109, "identity": 0.679166853427887, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ea8ae5dce15f1dded5ea4ed0ad13d907d9e021a566b24c4ca822f6bf5b4531af.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": "ea9f08c77e3fd7c042d596dc79f0d3abfa949faf7ccb2f148711ce28dfa2c12a", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5fe5ed8e297d53a415c70526630b3b5972a1361522b333bd939f3d6a8da2895d", "generation_seconds_batch": 24.778993019019254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07898585498332977, "target_z": -0.22070312220380284, "ce": 5.792276382446289, "genuineness": 4.570107460021973, "identity": 0.6210085153579712, "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_Infatuation/ea9f08c77e3fd7c042d596dc79f0d3abfa949faf7ccb2f148711ce28dfa2c12a.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "eaac1e93af27217d0bd68ae2507fde6489c89830ca160ac6c11bc79a127364eb", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "07759ead14e4384e5ebfe35728ce4b14d988f21f205bbf7b022475f523d0300d", "generation_seconds_batch": 26.164717542007565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3686310350894928, "target_z": 0.3144531256452763, "ce": 5.919358730316162, "genuineness": 4.319066047668457, "identity": 0.5448272824287415, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/eaac1e93af27217d0bd68ae2507fde6489c89830ca160ac6c11bc79a127364eb.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "eabf6ad8589cff17b8ce2bd1e4ca2ee018cc5d2091eb22fc9a79a8afaa19a8ca", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "56e8cfcd118b4248bb39baa1f2067274ee3151ecb6c923307f3458fe6fb531cd", "generation_seconds_batch": 17.87093402899336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23490798473358154, "target_z": 0.06738281067171724, "ce": 5.927301406860352, "genuineness": 3.9801597595214844, "identity": 0.3059082627296448, "hypothesis": "The 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_Infatuation/eabf6ad8589cff17b8ce2bd1e4ca2ee018cc5d2091eb22fc9a79a8afaa19a8ca.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "eb4e47db685beaf713c8786de064c42f5443c92674bfc150cfebdf6820230528", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "334a20e75736d2eef9960e9e89bd0eff6063fa9188ca74f7795344ed1acdbaf1", "generation_seconds_batch": 17.805468457983807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20570561289787292, "target_z": 0.013427720743538868, "ce": 6.078212261199951, "genuineness": 3.9048471450805664, "identity": 0.3377494513988495, "hypothesis": "The 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_Infatuation/eb4e47db685beaf713c8786de064c42f5443c92674bfc150cfebdf6820230528.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "eac20f3cc12fc4d6844254d41f0bb1c7bab8a001ec11dc3d00fb9a8bcd2e7077", "generation_seconds_batch": 16.77719493804034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.030359283089637756, "target_z": -0.3105468881206174, "ce": 6.1020402908325195, "genuineness": 4.093128204345703, "identity": 0.8312678337097168, "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_Infatuation/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "ec27242ca171ec5869db02c94a9eb1bc9bbd4189d7a6c91e458f1fb49bd48636", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4c2da8e00ffff93d6f7682830d73a40c676e1b3953a8a4a26a026987508e0a84", "generation_seconds_batch": 24.090061611961573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9891482591629028, "target_z": 1.4609374870944747, "ce": 5.847874641418457, "genuineness": 4.218649387359619, "identity": 0.3052268922328949, "hypothesis": "The 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_Infatuation/ec27242ca171ec5869db02c94a9eb1bc9bbd4189d7a6c91e458f1fb49bd48636.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": "ec2bf00c73ee3b8676fc0f607b81cd4232d4a125df514f7aa0c3ca6f41267e71", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dcf87b429bc264977068d0e1527b245f1a358610f4b0cf30b235afe996365d1a", "generation_seconds_batch": 24.01210499694571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3548887372016907, "target_z": 0.28906248537373797, "ce": 6.0305562019348145, "genuineness": 4.068024158477783, "identity": 0.501274585723877, "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_Infatuation/ec2bf00c73ee3b8676fc0f607b81cd4232d4a125df514f7aa0c3ca6f41267e71.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "ec3fa7cf7ea5b9878afa8b4a1e4175760b53eb4b8b0b4b64e60db73407c00ef2", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6801ceb6d26a9d035beb7368e3ddc926c30991edd7476b34f170de0b1b26a206", "generation_seconds_batch": 18.07707437092904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20914119482040405, "target_z": 0.019775394577317133, "ce": 6.141753673553467, "genuineness": 4.444586753845215, "identity": 0.7740335464477539, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ec3fa7cf7ea5b9878afa8b4a1e4175760b53eb4b8b0b4b64e60db73407c00ef2.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "ed0ef2862195662e0c460cb6f90be700f2c4ddfe01f9f0d7253828f013b20c31", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dbf17af27e8cf45bb5e376878b100507d4db30cea415b219996fe408b06813a0", "generation_seconds_batch": 23.945550378062762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05890096724033356, "target_z": -0.25781250258110505, "ce": 5.879645347595215, "genuineness": 4.632867813110352, "identity": 0.5693206787109375, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ed0ef2862195662e0c460cb6f90be700f2c4ddfe01f9f0d7253828f013b20c31.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": "ed1ddb9bb03510924b401c3f9b5ddf4ce080a86cbdbc7760952d843137f9728c", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12c7bd049f0fae863f19af0077a861a2e9c78eff38f56e19b3611c28005c4d90", "generation_seconds_batch": 18.022460600011982, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2882915139198303, "target_z": 0.16601565919964212, "ce": 5.609594821929932, "genuineness": 4.306513786315918, "identity": 0.6284111738204956, "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_Infatuation/ed1ddb9bb03510924b401c3f9b5ddf4ce080a86cbdbc7760952d843137f9728c.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "ed3b5a9875d01a574c2856520e2e1c476b32f3130e0f90cf6eaf7cb03f6e6d3c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f20737babcc85437812ba5936c148bf30bff6affef8800d794e814831231e48", "generation_seconds_batch": 23.49973385501653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07052905857563019, "target_z": -0.23632812736601297, "ce": 5.796247482299805, "genuineness": 4.218649387359619, "identity": 0.39122140407562256, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ed3b5a9875d01a574c2856520e2e1c476b32f3130e0f90cf6eaf7cb03f6e6d3c.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": "ed9484b6524cbc2a271ba8d75b8f8dd357b53438a6edd1e4e9609144c9a66760", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "714bee6fb408c0fd5f619261ccbdeefbef1699a625e5da6227a850b413fdfaca", "generation_seconds_batch": 23.363003949983977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20425210893154144, "target_z": 0.010742187607546045, "ce": 5.446769714355469, "genuineness": 4.419482707977295, "identity": 0.6541322469711304, "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_Infatuation/ed9484b6524cbc2a271ba8d75b8f8dd357b53438a6edd1e4e9609144c9a66760.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "edaeba4cb75b53dd10ac2cc6c13f5c79807fc00b25261bf6be2fb326c7712b2e", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fc16286e217e0c236f4bb36a9f453a1eeea753a0a39e1789e96f2b4532d96edf", "generation_seconds_batch": 23.5776075120084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12074127048254013, "target_z": -0.1435546901886511, "ce": 6.300607204437256, "genuineness": 4.595211505889893, "identity": 0.6758489608764648, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/edaeba4cb75b53dd10ac2cc6c13f5c79807fc00b25261bf6be2fb326c7712b2e.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "edf8004cd171b2ed8216a80be7fe24d90fd1b78926473eaa8bd198c315394055", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b7f8dd83fa964c44a56abf95dd891938f5c2a31360f297ed389e5af8f0c4fea5", "generation_seconds_batch": 22.969173456076533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20491279661655426, "target_z": 0.011962891996212066, "ce": 5.661221981048584, "genuineness": 4.250029563903809, "identity": 0.5072113275527954, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude haam. 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_Infatuation/edf8004cd171b2ed8216a80be7fe24d90fd1b78926473eaa8bd198c315394055.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "ee0f7392abd79a42604f4a6d1cf862b14cf5deaafb0f8facb318d5073a969b1b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa80c509816ad953b56d55c5afd07a04accaa9461855458d116c295c71206d2b", "generation_seconds_batch": 22.92770827910863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07792875170707703, "target_z": -0.22265625473202597, "ce": 5.863759994506836, "genuineness": 4.457139015197754, "identity": 0.4648396372795105, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ee0f7392abd79a42604f4a6d1cf862b14cf5deaafb0f8facb318d5073a969b1b.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "ee338eefd884f2254d6aac17570d8305128c3332293680363121d4ade2833aff", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2ac41f18f13e77077696b3232c9d4caadb9fd64d4f285ebbf7f57dd1c6264caa", "generation_seconds_batch": 25.239816828048788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22037287056446075, "target_z": 0.040527341652852135, "ce": 5.816103935241699, "genuineness": 4.413206577301025, "identity": 0.4321604073047638, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ee338eefd884f2254d6aac17570d8305128c3332293680363121d4ade2833aff.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "ee7c3de545be8324798f8a6995d2fd7b24c009ea0258b50e99c112d34a7d281f", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "abafc6814a703cc40197c19ebf2d51bf86f89116e6b2ecc2e5bc3178f6093c26", "generation_seconds_batch": 17.516738328966312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.01555989682674408, "target_z": -0.3378906333885915, "ce": 6.2767791748046875, "genuineness": 4.331617832183838, "identity": 0.37371787428855896, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ee7c3de545be8324798f8a6995d2fd7b24c009ea0258b50e99c112d34a7d281f.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": "ee83cca626bf073d2225ee4c9b76547cabccf7db8e52de64232b2e54eeaedf1e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "0c773665c09eee796c78e674c43f8982087d11647113838106dc6776a24b2abf", "generation_seconds_batch": 18.094224417000078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02718798816204071, "target_z": -0.3164062581734994, "ce": 5.927301406860352, "genuineness": 4.545003414154053, "identity": 0.47452670335769653, "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_Infatuation/ee83cca626bf073d2225ee4c9b76547cabccf7db8e52de64232b2e54eeaedf1e.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "eea2e9adc236dbb271eec4213bbdbb63bd8bdf9caab50ceeedd5b07bef94c705", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dddcf1845ec34d663627fc6f72bcf720a7d86119973a1d6e37e588160f0d7b89", "generation_seconds_batch": 24.765150011051446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21132145822048187, "target_z": 0.023803708047200056, "ce": 6.395919322967529, "genuineness": 4.469690799713135, "identity": 0.4452008605003357, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/eea2e9adc236dbb271eec4213bbdbb63bd8bdf9caab50ceeedd5b07bef94c705.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "ef537c4a328908f6c7ce5d110261344f7a4ee5007eac19171fb34aa54afe14a7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5f1697046e643c16aa037fac880dabdbfd94efa3ea0e80df84ba4acd71e515dc", "generation_seconds_batch": 24.373071242007427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12866951525211334, "target_z": -0.12890625129055253, "ce": 5.935244083404541, "genuineness": 4.6203155517578125, "identity": 0.3832664489746094, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ef537c4a328908f6c7ce5d110261344f7a4ee5007eac19171fb34aa54afe14a7.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": "ef8fb9a9c49f1887cb9f6f71b3aa785333a26c7d988ad271995588191df57bdb", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "3f5b4fbd36d4daafbf1c68c64c3af51599344aa11db883c54599dc4823ff547a", "generation_seconds_batch": 18.462183596100658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059958070516586304, "target_z": -0.25585937005288195, "ce": 5.847874641418457, "genuineness": 4.645420074462891, "identity": 0.8267472982406616, "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_Infatuation/ef8fb9a9c49f1887cb9f6f71b3aa785333a26c7d988ad271995588191df57bdb.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "efcfce239ef6e185e91fae48cb66dda17cf275b9e00b468dce6b85ac0d82ce16", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cd22157d56e63987a4325861818ab69e7755d03430dc3cfffb4f75429330cc8d", "generation_seconds_batch": 24.406904053059407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.035644784569740295, "target_z": -0.3007812530112892, "ce": 6.300607204437256, "genuineness": 4.293961524963379, "identity": 0.4966640770435333, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/efcfce239ef6e185e91fae48cb66dda17cf275b9e00b468dce6b85ac0d82ce16.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "f008670a2c88308b35bb7fe6e7a312fd10606141915aac66219e6a30d5b713a9", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "89564e7e8eb94df36463a7c796bc2ab0148ca57967c53e4aaa4f667bb60bd126", "generation_seconds_batch": 23.864897417020984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05044417083263397, "target_z": -0.2734375077433152, "ce": 5.6334228515625, "genuineness": 4.7332844734191895, "identity": 0.524074137210846, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f008670a2c88308b35bb7fe6e7a312fd10606141915aac66219e6a30d5b713a9.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "f02b976a21e13a709edca718254cb37b9520aac8a8891d3a76fc19523a9a4c48", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c0c2e2c85d71e93c0d05c0fb417baf036e521661c37b2dbdcab6b9b3b76a60d9", "generation_seconds_batch": 22.88149489206262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45108479261398315, "target_z": 0.4667969122109314, "ce": 5.546053409576416, "genuineness": 4.017816066741943, "identity": 0.5078485012054443, "hypothesis": "The door still open. I put your coat 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_Infatuation/f02b976a21e13a709edca718254cb37b9520aac8a8891d3a76fc19523a9a4c48.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "f0468ac9a1d2f3e3988691474ce849e16e1b23668fe7dfe977c94cfa8ae73b4c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "89c89c200720b97be800c157cf5968e949c56cf64e64ea243e830e5a3f6b3778", "generation_seconds_batch": 28.562153213075362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0906298160552979, "target_z": 1.6484375490409962, "ce": 5.967014789581299, "genuineness": 4.413206577301025, "identity": 0.3912771940231323, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f0468ac9a1d2f3e3988691474ce849e16e1b23668fe7dfe977c94cfa8ae73b4c.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "f07d696adf33f0275c360abc5ee6cc649deea4246d2c8da817cb2a2f26bc2432", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "db604ee01dabe032c071517434ca887084b457f9225b1dc9fb6ece2fff12cab9", "generation_seconds_batch": 25.828103650943376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05572967231273651, "target_z": -0.263671872633987, "ce": 5.6254801750183105, "genuineness": 4.243753433227539, "identity": 0.5319667458534241, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f07d696adf33f0275c360abc5ee6cc649deea4246d2c8da817cb2a2f26bc2432.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": "f094d07a041006bf4ed3814c5f90e0937846a30eb10dff8a20b8565f74ecea59", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a046621cadc867b0532561c5663f446b1c54254a628896b7274f47094ee619a8", "generation_seconds_batch": 17.712037838995457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1640823483467102, "target_z": -0.06347654561527102, "ce": 5.982900142669678, "genuineness": 4.582659721374512, "identity": 0.5247330069541931, "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_Infatuation/f094d07a041006bf4ed3814c5f90e0937846a30eb10dff8a20b8565f74ecea59.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "f09ad32eff868b33e6dd6e99d9839215af3e1620eaf79bdda9c2917b766cd5a7", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d937073a56e189973a795156d4f871c9cf8cb735465e45ab5975d3c179b1a287", "generation_seconds_batch": 17.369714931002818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17504973709583282, "target_z": -0.04321290232063233, "ce": 5.450741291046143, "genuineness": 4.256305694580078, "identity": 0.18293039500713348, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f09ad32eff868b33e6dd6e99d9839215af3e1620eaf79bdda9c2917b766cd5a7.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "f09afdc59d0b5f78d7b0bca43e54db677938301bb110491bb30fb519ad6f4c4c", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5d7c77036a7e7e9e38b192cba0335c5e8de87fd4803811f15499eb6f2b266f27", "generation_seconds_batch": 24.119457418099046, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04621577262878418, "target_z": -0.28125001032442026, "ce": 5.685050010681152, "genuineness": 4.369274139404297, "identity": 0.5960876941680908, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f09afdc59d0b5f78d7b0bca43e54db677938301bb110491bb30fb519ad6f4c4c.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "f0fccf08d38b274e149c215d329a8c5edc37bb640410254216f0344cc8dfff20", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "57b8ab732c86cfba2e7ac3f965c7e944cf5c17c2fb6e7067c61ff04a15c7bf09", "generation_seconds_batch": 17.590119868982583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.040930286049842834, "target_z": -0.29101561790196107, "ce": 6.1894097328186035, "genuineness": 4.331617832183838, "identity": 0.5205230712890625, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f0fccf08d38b274e149c215d329a8c5edc37bb640410254216f0344cc8dfff20.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "f11d6b4fdef768ae7e15aaedac0eec384f44111ef4c400923bae345f368e34ce", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "317037f1ab76eb36511972e839bb00a9f5b2bb1453ac0c03fffd78056046d3e4", "generation_seconds_batch": 23.21542852197308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1991317868232727, "target_z": 0.0012817423612780608, "ce": 6.38797664642334, "genuineness": 4.432034492492676, "identity": 0.422112375497818, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f11d6b4fdef768ae7e15aaedac0eec384f44111ef4c400923bae345f368e34ce.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": "f19fad00697c0f586598f8eb9e593c75ed07ace5fb3478e96ec5f2593db9e95e", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "d35c871bbafef4ddb57f28df478ab9d9aab135bbea4f7249fab3f492dbcd0d34", "generation_seconds_batch": 17.487678276957013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21330352127552032, "target_z": 0.027465821213198124, "ce": 6.260893821716309, "genuineness": 4.507347106933594, "identity": 0.2838285267353058, "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_Infatuation/f19fad00697c0f586598f8eb9e593c75ed07ace5fb3478e96ec5f2593db9e95e.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "df6d609a152aaca99657da04caf80ada4fef5520b0922aff3e2293cc12550dd6", "generation_seconds_batch": 16.938520982977934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0018176138401031494, "target_z": -0.3632812461283424, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.7379372119903564, "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_Infatuation/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.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": "f2ce96ec66b69728a29b25c509fbd83c32514a697236837911b06c905f7950bf", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2335ce63679ec39cfab2cb847abe8b2fd09927515e619842e34d3f1e9ba99fe4", "generation_seconds_batch": 24.01421528996434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0663006603717804, "target_z": -0.24414062994711805, "ce": 5.998785495758057, "genuineness": 4.432034492492676, "identity": 0.47471004724502563, "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_Infatuation/f2ce96ec66b69728a29b25c509fbd83c32514a697236837911b06c905f7950bf.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "f3be0a64cb866947d0be086d9eb2fd81c53d35b5079675519cb6db8a275329b8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d5b86effe861bfc5eac185d090e76356fec32058a4e6c6a0aa88f832a7ec0713", "generation_seconds_batch": 23.52528971794527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45108479261398315, "target_z": 0.4667969122109314, "ce": 6.054384231567383, "genuineness": 4.030367851257324, "identity": 0.23476578295230865, "hypothesis": "The 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_Infatuation/f3be0a64cb866947d0be086d9eb2fd81c53d35b5079675519cb6db8a275329b8.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": "f3e181fc9506fc11477a8130dfb602b1efe71c11c3d51507ca11a9230286edd6", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "dd2c343a3e7436b4ba7e1b76789dabddbc75e834b0c82efa8adea9425af23b41", "generation_seconds_batch": 19.79489864804782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.033530592918395996, "target_z": -0.30468749053594807, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.5517277717590332, "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_Infatuation/f3e181fc9506fc11477a8130dfb602b1efe71c11c3d51507ca11a9230286edd6.mp3" }, { "id": "emo_Infatuation-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-1", "key": "f3fa84b7f496051e648700ffc873a9f27db59ab2738180c31465291f6cdae468", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1c223a64d77ce76b07492e08a354427df76811256bea936c0d42b977dfa29398", "generation_seconds_batch": 23.185560903977603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20788589119911194, "target_z": 0.017456061745209167, "ce": 6.022613525390625, "genuineness": 4.607763767242432, "identity": 0.4441266357898712, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f3fa84b7f496051e648700ffc873a9f27db59ab2738180c31465291f6cdae468.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "f4ad76a20463fc0fe6e18f0ef5f23800fcbdd1e367fdb349eb9dad42c033779b", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ce5834ed5a6076c0f9ed7e9cfbc82fc63db44a24cb3a71b7d4e84872f5bf6489", "generation_seconds_batch": 18.72399408998899, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25710707902908325, "target_z": 0.10839845610546568, "ce": 5.240260601043701, "genuineness": 4.444586753845215, "identity": 0.614001989364624, "hypothesis": "La porte est encore ouverte, j'ai poussé ton manteau sur la chaise, tais-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f4ad76a20463fc0fe6e18f0ef5f23800fcbdd1e367fdb349eb9dad42c033779b.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "f4b7cfe722880a1405f128a1d074419b0d2811f6c34b9a1b2517a63df9307a87", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c9995e2eb66ebb9f0debad45532350ef97466e7f029deefa3452087ba4aeddf1", "generation_seconds_batch": 22.969173456076533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00029659271240234375, "target_z": -0.3671875111847886, "ce": 5.2223896980285645, "genuineness": 4.055472373962402, "identity": 0.4461211562156677, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f4b7cfe722880a1405f128a1d074419b0d2811f6c34b9a1b2517a63df9307a87.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "f52b4d8165313bdbae9859c90a8ab73e862c866035bd3bfef497d167e4c58123", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "29c5f022559d5e57cb507a97718c450f92cecc604b8db2a98556605659246754", "generation_seconds_batch": 18.283402662025765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39188721776008606, "target_z": 0.35742187607546044, "ce": 5.847874641418457, "genuineness": 4.7081804275512695, "identity": 0.5710322260856628, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f52b4d8165313bdbae9859c90a8ab73e862c866035bd3bfef497d167e4c58123.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "f55e1ca6dced52c73e8c509b9475e670c9961add3ea094b8e88c513d83834d61", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1e8f654f4bc0a6181a66d4fc56e5633930e0bbd806d47bc8e45a492fb1f201c8", "generation_seconds_batch": 23.120152138988487, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004524990916252136, "target_z": -0.3750000137658937, "ce": 6.252951145172119, "genuineness": 4.362998008728027, "identity": 0.5409306287765503, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f55e1ca6dced52c73e8c509b9475e670c9961add3ea094b8e88c513d83834d61.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "f56ca07fdded5a68c7c78d00a8f68927b788cc109de081c1178e6c8525b5a6de", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "07ecc0d778755ab84dc670c1c45bc5c47d6da8ee85a53324f7611a6771dff5a3", "generation_seconds_batch": 32.215818403987214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 6.181467056274414, "genuineness": 4.068024158477783, "identity": 0.3820493221282959, "hypothesis": "The 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_Infatuation/f56ca07fdded5a68c7c78d00a8f68927b788cc109de081c1178e6c8525b5a6de.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "f59fdaa69828a07f0f2562ff790985b68a01c690260327f19919df46f55a9751", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c3f606ddb5114c728fec00b956300a7a9b6583bcb9834384480d389cde40f98b", "generation_seconds_batch": 17.43683027906809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 6.316492557525635, "genuineness": 4.68307638168335, "identity": 0.6407157182693481, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f59fdaa69828a07f0f2562ff790985b68a01c690260327f19919df46f55a9751.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "f5b80ddc12b33e2b6e130dfa81b9936965321eabafcf63947451091985dc8041", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "387fa93ec71ab8737b83b2867aa8934590727bdddea2ef17d788ca25409779b7", "generation_seconds_batch": 23.625405644997954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.024016693234443665, "target_z": -0.32226562822638133, "ce": 6.062326908111572, "genuineness": 4.356721878051758, "identity": 0.42064759135246277, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f5b80ddc12b33e2b6e130dfa81b9936965321eabafcf63947451091985dc8041.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "f5cada84663fa7a9024f26f733ff3b82252f8cabf5e7282469201e7f32dda565", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "43855acc91d7cf7e62f4e3a5d0a1a0dabc3315fcea2e74ec6fdc5b4140084846", "generation_seconds_batch": 26.251655403058976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3548887372016907, "target_z": 0.28906248537373797, "ce": 5.839932441711426, "genuineness": 4.331617832183838, "identity": 0.41957926750183105, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f5cada84663fa7a9024f26f733ff3b82252f8cabf5e7282469201e7f32dda565.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "f5d360a8f79d388fb671df2a14f467f921701e4a5090ce3a0bd27e20bb5c88c1", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f7551c1700d881ca56a3ca705d69ad3655011ab0c35f02604e0814f6a6f74e1c", "generation_seconds_batch": 23.57174812804442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09801363945007324, "target_z": -0.18554687435472372, "ce": 5.95112943649292, "genuineness": 4.645420074462891, "identity": 0.7786741852760315, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f5d360a8f79d388fb671df2a14f467f921701e4a5090ce3a0bd27e20bb5c88c1.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "f6653dc687e4268bac76443252adb1d1d3a8b3b2f156430f1614486520261851", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7cce6259c75f0bf30c50fc24b4326a71f634e508f2f4ed1c4941f74be8bb77ed", "generation_seconds_batch": 26.381115291966125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3258185386657715, "target_z": 0.2353516023995825, "ce": 5.796247482299805, "genuineness": 4.293961524963379, "identity": 0.3604341149330139, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f6653dc687e4268bac76443252adb1d1d3a8b3b2f156430f1614486520261851.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": "f688d7b411d2f97d2a442debea576703cc746859114931cc3509e996c41822b5", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "60f894a7da32347b908fbe85d2933d59e314ede092234efc7e2b031b304341dd", "generation_seconds_batch": 20.791441719047725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003931805491447449, "target_z": -0.35937500860368354, "ce": 6.173524379730225, "genuineness": 4.068024158477783, "identity": 0.5794442892074585, "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_Infatuation/f688d7b411d2f97d2a442debea576703cc746859114931cc3509e996c41822b5.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": "f69f4f37e760100e883fcee017d1d17b3b8165b770fe3e93dbfcfe990bd615bf", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "70e9a6eb1adbd4be381a72b767a81077f0dbb3ae7226c970b7180ebf171821fa", "generation_seconds_batch": 20.29180718306452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 6.1894097328186035, "genuineness": 4.494794845581055, "identity": 0.551543116569519, "hypothesis": "De weg gaat linksaf naar de brug, loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f69f4f37e760100e883fcee017d1d17b3b8165b770fe3e93dbfcfe990bd615bf.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "f6b5e6f40ea9365336cdb37665751fe9d31a400a85549bcfc9522a013df7a896", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5fceb197e49de19fe2358daf8493283784e84faefd45bb07fa6178b105546c2d", "generation_seconds_batch": 17.892526929965243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09748508781194687, "target_z": -0.1865234406188353, "ce": 4.789514064788818, "genuineness": 4.118232727050781, "identity": 0.3386101722717285, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f6b5e6f40ea9365336cdb37665751fe9d31a400a85549bcfc9522a013df7a896.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "f6b8bb95f8bc54058c5cf61a3d4eb9e2edf2c03f8fb0e46f3226675d2fc500cc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2948ee0d2a9a893b65680f110fa24dc474e8dec80d42b99a0b73ec5874b5074e", "generation_seconds_batch": 18.094562384998426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35171744227409363, "target_z": 0.283203115320856, "ce": 5.605623245239258, "genuineness": 4.287685871124268, "identity": 0.4486371874809265, "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_Infatuation/f6b8bb95f8bc54058c5cf61a3d4eb9e2edf2c03f8fb0e46f3226675d2fc500cc.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": "f6ba3c6d695f91d06c0cee413dfd604555e5c433d41915f95f4ea33275bc5c69", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "1e9998cd5eba95be6a6bc04c97398fe9dfcf928f6a564269ee34def01f2756a4", "generation_seconds_batch": 18.434974618954584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07264326512813568, "target_z": -0.23242186230956677, "ce": 5.863759994506836, "genuineness": 4.607763767242432, "identity": 0.512648344039917, "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_Infatuation/f6ba3c6d695f91d06c0cee413dfd604555e5c433d41915f95f4ea33275bc5c69.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "f71692a07b8adebd85dd52b75ff6a41be256872d75f13b25c084843a9a99f004", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f40ada2198f194b4ae548cdc44925ca60f238433a06206bf78dbb6593646fcfa", "generation_seconds_batch": 23.55227124004159, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19374719262123108, "target_z": -0.008666979134098857, "ce": 6.0305562019348145, "genuineness": 3.973883628845215, "identity": 0.43856924772262573, "hypothesis": "The 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_Infatuation/f71692a07b8adebd85dd52b75ff6a41be256872d75f13b25c084843a9a99f004.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "f75d72d7d2dff02dbc594289299a3c5a25a6389f84eab580aeea2b8daee0b389", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1b12ff403215940e9a384c3f97266a2cb7be127c39a3b1e64dbb79ae77aee5d1", "generation_seconds_batch": 16.744452214916237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2578998804092407, "target_z": 0.10986325732100512, "ce": 5.744620323181152, "genuineness": 4.65797233581543, "identity": 0.5864353179931641, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f75d72d7d2dff02dbc594289299a3c5a25a6389f84eab580aeea2b8daee0b389.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": "f78ca9389e1998fffc2f682d29b60b01012dc7299f11c3c71a0e0349224332fa", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "aa69dd46e0066fa82265dd93d88f80e1924a366f00e7f0ba78387a9f8d20c0d6", "generation_seconds_batch": 18.948122014990076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16910356283187866, "target_z": -0.05419921428683916, "ce": 6.046441555023193, "genuineness": 4.532451152801514, "identity": 0.748631477355957, "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_Infatuation/f78ca9389e1998fffc2f682d29b60b01012dc7299f11c3c71a0e0349224332fa.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "4131d2396fc2b864d2c5bee66b60b83dcf4e655e2353c26ac79df2ed5a978fd2", "generation_seconds_batch": 16.877082854975015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198737442493439, "target_z": -0.2890625129055253, "ce": 6.316492557525635, "genuineness": 4.545003414154053, "identity": 0.5839731693267822, "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_Infatuation/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Infatuation-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-1", "key": "f7db3c6885e60d0aa7ebd3f2498b5cabbb8d5ddb9141514b5dd40d13748999fa", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c37c276f3e14c715354ce01b2f01b01d5b2f69c62aa1b1c7a6a3860f9fe9b336", "generation_seconds_batch": 23.733570913085714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05150127410888672, "target_z": -0.2714843752150921, "ce": 6.2767791748046875, "genuineness": 4.65797233581543, "identity": 0.5309805274009705, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f7db3c6885e60d0aa7ebd3f2498b5cabbb8d5ddb9141514b5dd40d13748999fa.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": "f7e5e6e90341789fe6c874b95605937b762f8a44bb573959c4a8ac9e78ab560f", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": "c0d93eabaf38f7b38c22dd374f411b332943be616f1cd55b995c0a0848962d93", "generation_seconds_batch": 18.99105284595862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25129303336143494, "target_z": 0.09765626849791964, "ce": 6.340320587158203, "genuineness": 4.607763767242432, "identity": 0.38263434171676636, "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_Infatuation/f7e5e6e90341789fe6c874b95605937b762f8a44bb573959c4a8ac9e78ab560f.mp3" }, { "id": "emo_Infatuation-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-es-0", "key": "f81f84d8e90680a21a0eca6eb54f1258263aa260009061fa00bf7a764355c293", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "99af94dc7546b6abd1596b4c9dcd6ac438f2612365b325e7549f783d71f414c7", "generation_seconds_batch": 26.038742668926716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.018731191754341125, "target_z": -0.33203126333570954, "ce": 6.308549880981445, "genuineness": 4.394378662109375, "identity": 0.39205819368362427, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f81f84d8e90680a21a0eca6eb54f1258263aa260009061fa00bf7a764355c293.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_Infatuation", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": "2f83b048168742c6f6ec3a16c7505799aafa445dea72ba460dcf8da34f99ec22", "generation_seconds_batch": 20.41174220503308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04198737442493439, "target_z": -0.2890625129055253, "ce": 6.38797664642334, "genuineness": 4.300237655639648, "identity": 0.6349616646766663, "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_Infatuation/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "f8c0770f4322c3cca9751b88c1a1326c74a35369fa281f08b312ec93d5919126", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6dcde1a1170c3daf206b7cc840d3e2dae23fb683ca86b486ffd8f5eb03d524cc", "generation_seconds_batch": 24.54299266601447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.908808708190918, "target_z": 1.3124999655852658, "ce": 5.804190158843994, "genuineness": 4.65797233581543, "identity": 0.7066922187805176, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/f8c0770f4322c3cca9751b88c1a1326c74a35369fa281f08b312ec93d5919126.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": "f9996dbb79f87ad9616bc71bfbdfc357f08e6eb3766b23da5b230916b5ff995b", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1a034a70595d59f06c6b4e1199190741176514b2adb18b1796d65fd9656852d", "generation_seconds_batch": 28.56448591791559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 5.323658466339111, "genuineness": 4.18099308013916, "identity": 0.39638057351112366, "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_Infatuation/f9996dbb79f87ad9616bc71bfbdfc357f08e6eb3766b23da5b230916b5ff995b.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "f9c14486b6bfb15be0f0c281660532016fabee66300b7a125e50415f522a3955", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6d5bfe2f340662ef3d0e7f9b46775832a16dec75f96b7aa881a0de23be6660ad", "generation_seconds_batch": 23.20984889206011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00029659271240234375, "target_z": -0.3671875111847886, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.7417905330657959, "hypothesis": "De deur 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_Infatuation/f9c14486b6bfb15be0f0c281660532016fabee66300b7a125e50415f522a3955.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "fa34cdfe8efbfe2effcfca1d9bb156b015bfe76555179ca08d6c88b3e73d81be", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f3f28c1f61fedffacc13b0b191e2066696c889f659c7ca402dcad6718f40acb9", "generation_seconds_batch": 17.4639029300306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1813923418521881, "target_z": -0.03149413468308104, "ce": 5.760505676269531, "genuineness": 4.331617832183838, "identity": 0.2742553949356079, "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_Infatuation/fa34cdfe8efbfe2effcfca1d9bb156b015bfe76555179ca08d6c88b3e73d81be.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "fa5a276c5ffbdf436ec187048d8be0b6917cf29a4abbe494926e84e8c5b9fbf6", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "742d4b0b6d6f428cba0da5aec65f50009cbfd23466e854b3e2c200f7e606ef35", "generation_seconds_batch": 25.0020321670454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20848050713539124, "target_z": 0.01855469018865111, "ce": 6.149696350097656, "genuineness": 4.645420074462891, "identity": 0.7930839657783508, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fa5a276c5ffbdf436ec187048d8be0b6917cf29a4abbe494926e84e8c5b9fbf6.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "fa739a12b749177c3f646fb64152eb65679997d1f453dbf2852f3d12d3327094", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f088ef94cd9726e5250021de775d07f6bd289bca676c1d9782d8b8b0cb38be4", "generation_seconds_batch": 22.83276259608101, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11387012898921967, "target_z": -0.1562499965585266, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.7495722770690918, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fa739a12b749177c3f646fb64152eb65679997d1f453dbf2852f3d12d3327094.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": "fad2c5857c7d0d78e24704f2eb80cdd093922e19eb2f2f4dc07a946bb149fd52", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08cd4abb4bb60fb80a89af1e236ce49a025e04599b57881ae138b6cc96353723", "generation_seconds_batch": 17.182931135059334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05150127410888672, "target_z": -0.2714843752150921, "ce": 5.982900142669678, "genuineness": 4.65797233581543, "identity": 0.6561551690101624, "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_Infatuation/fad2c5857c7d0d78e24704f2eb80cdd093922e19eb2f2f4dc07a946bb149fd52.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "fad7f4c6e82351e31bc4925571c4d6f16c847acdac9dcf9be650efd8d5032494", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b1c71992107c7866acb72839a0d3209e09bd98603b4ca1a36587515687369304", "generation_seconds_batch": 26.478070206940174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.047272875905036926, "target_z": -0.27929687779619716, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.3248799443244934, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fad7f4c6e82351e31bc4925571c4d6f16c847acdac9dcf9be650efd8d5032494.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "fb77125137491342c1f719dee092fc36b9c0f87b8fafc62608991b87463f1aae", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c9489d8e24ac7dc2cbd7b2141ecf38e248c489361f380da1674b67a0074554b2", "generation_seconds_batch": 25.13456731790211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15879684686660767, "target_z": -0.0732421807245992, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.12474168837070465, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fb77125137491342c1f719dee092fc36b9c0f87b8fafc62608991b87463f1aae.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": "fb7fed4d29c02b883924ffcf2076fe827d0630d631b435ae4b24f701b72e61d4", "bucket": "emo_Infatuation", "phase": "heldout", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "850001c95fa847871ef57e80c7b4401acb94af2c77ae2cadb27cde440ab999a4", "generation_seconds_batch": 28.56448591791559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004988908767700195, "target_z": -0.35742187607546044, "ce": 5.959072113037109, "genuineness": 4.6705241203308105, "identity": 0.41422945261001587, "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_Infatuation/fb7fed4d29c02b883924ffcf2076fe827d0630d631b435ae4b24f701b72e61d4.mp3" }, { "id": "emo_Infatuation-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-0", "key": "fb89b5f707a1f6449c6fbec8b5b4a2b04cc32fbc1a63a64f67efd339029041c8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] The door is still open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] I put your coat on the chair.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6ff9803460e1cc94a0e9d7cc49134e0f250be28f3a7539d2092d3d715c80307f", "generation_seconds_batch": 24.192611722042784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5071110129356384, "target_z": 0.5703124681663708, "ce": 5.982900142669678, "genuineness": 3.8420867919921875, "identity": 0.33751583099365234, "hypothesis": "The 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_Infatuation/fb89b5f707a1f6449c6fbec8b5b4a2b04cc32fbc1a63a64f67efd339029041c8.mp3" }, { "id": "emo_Infatuation-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-de-0", "key": "fb93b027dcd667afb423f5b5bd483de2e61b04e34f1f0156cc6b0d36cb66d657", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e326df9e193d14e83028618d665df72a9d42ca84daf3edecfc5939b46d494bb9", "generation_seconds_batch": 22.47107587393839, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20127901434898376, "target_z": 0.0052490178585489445, "ce": 5.80021858215332, "genuineness": 4.607763767242432, "identity": 0.49617230892181396, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fb93b027dcd667afb423f5b5bd483de2e61b04e34f1f0156cc6b0d36cb66d657.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "fbcab38054a2bd769182c2328e8ee72bef7fa8a7cc7967822e7b3c8b85934dcd", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1c2ddf5382db60bb7306bd82504ea26567bbccb9231fc1bd86a752699b56c8e", "generation_seconds_batch": 24.05426055600401, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.553623378276825, "target_z": 0.6562499690267392, "ce": 5.764476776123047, "genuineness": 4.68307638168335, "identity": 0.5872085094451904, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fbcab38054a2bd769182c2328e8ee72bef7fa8a7cc7967822e7b3c8b85934dcd.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "fc027a1c2c82466bdc3275c21bbbb260c6ece11a69b39a27e52697f457dbc5df", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "34c01d50307a9043e26404e0dc69060b5e6727bac1151083ee4f4be59a72f9fd", "generation_seconds_batch": 23.88752032094635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.004988908767700195, "target_z": -0.35742187607546044, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.7182309627532959, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fc027a1c2c82466bdc3275c21bbbb260c6ece11a69b39a27e52697f457dbc5df.mp3" }, { "id": "emo_Infatuation-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-0", "key": "fe10e0af56cf187e15c92482ee255a87def4cd920bda7b9cd78b4fb6e61025d3", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] De deur staat nog open.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1919831983cdb09b31f595d7637af360f29851e97dd1808c715059223228bc0b", "generation_seconds_batch": 17.965882760006934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0007605105638504028, "target_z": -0.3652343786565655, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.7247387170791626, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fe10e0af56cf187e15c92482ee255a87def4cd920bda7b9cd78b4fb6e61025d3.mp3" }, { "id": "emo_Infatuation-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-0", "key": "fe4fcd58252f5db695b966b0f2e28e68d11e65299ca1ba347fb003a78d27c0fc", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "94c50a3f559bcdd528cf4961b425732e1edf254b32ec6df0e9e4dda822a56735", "generation_seconds_batch": 23.768604438053444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.429942786693573, "target_z": 0.42773437177361867, "ce": 6.078212261199951, "genuineness": 4.808597087860107, "identity": 0.7217413783073425, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fe4fcd58252f5db695b966b0f2e28e68d11e65299ca1ba347fb003a78d27c0fc.mp3" }, { "id": "emo_Infatuation-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-fr-1", "key": "fe7359ced74b10ab8f6b470b5dcb12c8b76cb62dcbe77cc793d4a42f2b3e5053", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9584dbbe40bed01294c04a72546a3a4dc9d29c4269b771ce9ad5beaa8ef5f635", "generation_seconds_batch": 26.08297708106693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11069882661104202, "target_z": -0.16210938037730221, "ce": 6.109982967376709, "genuineness": 4.632867813110352, "identity": 0.7919948101043701, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/fe7359ced74b10ab8f6b470b5dcb12c8b76cb62dcbe77cc793d4a42f2b3e5053.mp3" }, { "id": "emo_Infatuation-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-nl-1", "key": "ff65b69aca33419548bfbf65fe194b6c14fdae76df0dfc0bf270a9a5760fbbc8", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] Het stond naast het oude raam.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4cf8548f4defb9a588110df151e9086e9949b00df92512a450d7e3e2d3d3824c", "generation_seconds_batch": 22.907625347026624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6022499799728394, "target_z": 0.7460937900071285, "ce": 5.629451274871826, "genuineness": 4.18726921081543, "identity": 0.45235005021095276, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ff65b69aca33419548bfbf65fe194b6c14fdae76df0dfc0bf270a9a5760fbbc8.mp3" }, { "id": "emo_Infatuation-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Infatuation-en-1", "key": "ffbef8ce10125d5c0454fe5ad1c69f2f72c4e4c31ea427477ac90cdea26e0e13", "bucket": "emo_Infatuation", "phase": "grid", "candidate": "manual-e0a2c5b12b00", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Manipulate vocal projection subtly; the emotion should be felt more than loudly stated, a warm intimacy.\nSCRIPT:\n(Begin at a hushed, intimate volume, as if sharing a secret only with the listener.) [3.2 seconds duration] I found the little box.\n(Allow the volume to swell ever so slightly mid-phrase, a momentary rush of feeling.) [3.8 seconds duration] It was beside the old window.\n(Bring the volume back down to a near whisper for the final words, sealing the private moment.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0513b3178869681a8dd45f3ceddab45a8b300c459ed10e5c2474c491fd2fb056", "generation_seconds_batch": 24.00509573495947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3015052378177643, "target_z": 0.19042969190938783, "ce": 5.696964263916016, "genuineness": 4.193545341491699, "identity": 0.4285166263580322, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Infatuation/ffbef8ce10125d5c0454fe5ad1c69f2f72c4e4c31ea427477ac90cdea26e0e13.mp3" }, { "key": "original-emo_Infatuation-de-0-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "0dca6b95c3068f35b4a499072f5c350f2f20eb7588235e0405d53859aa5f13f9", "task_id": "emo_Infatuation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.05737994611263275, "target_z": -0.47265625473202594, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.5088326334953308, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/93568cac460fee5a76056b39.mp3" }, { "key": "original-emo_Infatuation-de-0-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "80d4f2101912c51fce4d939a7fce3962ef44bb394cb64fd15f2aee0e8661dd76", "task_id": "emo_Infatuation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.0563228577375412, "target_z": -0.47070314973559024, "ce": 6.181467056274414, "genuineness": 4.400654315948486, "identity": 0.7179945111274719, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/30566e297a1fc4e3429004e3.mp3" }, { "key": "original-emo_Infatuation-de-0-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "7567b8eaf6c1120c103ce9667e21cbb5b339947cf0a12a3409eedc419c94b4b2", "task_id": "emo_Infatuation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.032009556889534, "target_z": -0.42578123924539557, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.476750910282135, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/43a47acd365b21588183c700.mp3" }, { "key": "original-emo_Infatuation-de-0-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "dfc4e9b49f0770cfefe33ff64cf1e4e45546e655f47c053e2c485d34c4eb1128", "task_id": "emo_Infatuation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.018267273902893066, "target_z": -0.4003906265056446, "ce": 6.308549880981445, "genuineness": 4.507347106933594, "identity": 0.5540797114372253, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/cc8a1a52da33b8708897ea83.mp3" }, { "key": "original-emo_Infatuation-de-0-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "438efe088816baa6cbacc77d67fc94d8a64ac66a3c456c0a08d658b3da48ae19", "task_id": "emo_Infatuation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.03412376344203949, "target_z": -0.42968750430184177, "ce": 6.181467056274414, "genuineness": 4.2249250411987305, "identity": 0.5618908405303955, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/12ba384151191b8587d59c2a.mp3" }, { "key": "original-emo_Infatuation-de-0-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "f72d64eadbdcc1d59d1abe862b8993d4b61a03e9f87263af987495e2f1c1cdbc", "task_id": "emo_Infatuation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.02249567210674286, "target_z": -0.40820312908674966, "ce": 6.205295085906982, "genuineness": 4.469690799713135, "identity": 0.6267285346984863, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/bcc8b1d3078334c95bd9f059.mp3" }, { "key": "original-emo_Infatuation-de-0-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "f92e74b3343ad1d1975d677047187a0ab66666c591a4fa4dde9ed4cf51cfb40f", "task_id": "emo_Infatuation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.018731191754341125, "target_z": -0.33203126333570954, "ce": 6.022613525390625, "genuineness": 4.049196243286133, "identity": 0.4694957733154297, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/0724ac682ac42660bf5c5a98.mp3" }, { "key": "original-emo_Infatuation-de-0-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "38ade9dc526388980f60facb38bc8022ee019711a3f7df11509bfa13546d3d9d", "task_id": "emo_Infatuation-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.07429353892803192, "target_z": -0.5039062650564462, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.44395923614501953, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/c6d409e653178a86019424c3.mp3" }, { "key": "original-emo_Infatuation-de-1-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "6b769714e82a36296d4863d47e348e42e9388b9640ecf42353d32678b16b2e32", "task_id": "emo_Infatuation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.010274410247802734, "target_z": -0.3476562409661323, "ce": 6.332377910614014, "genuineness": 3.9425034523010254, "identity": 0.5871721506118774, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/01f3aa0054b520ec8e27c1a6.mp3" }, { "key": "original-emo_Infatuation-de-1-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "5ae9814534d921da9dc0299d3a69d7ae03ffc111c0c00e26894f5de9a7fae0da", "task_id": "emo_Infatuation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.03458768129348755, "target_z": -0.3027343855395124, "ce": 6.395919322967529, "genuineness": 4.231201171875, "identity": 0.3371354639530182, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/6ba746e707ec0924bd822f5e.mp3" }, { "key": "original-emo_Infatuation-de-1-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "cfbbfb707546c20a5787b6b905365dfad2ea7b0cb35098f7011a110c1f58bf36", "task_id": "emo_Infatuation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.05150127410888672, "target_z": -0.2714843752150921, "ce": 6.515059471130371, "genuineness": 4.356721878051758, "identity": 0.5268768072128296, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/c9c4cadbb5f49d1912e10d43.mp3" }, { "key": "original-emo_Infatuation-de-1-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "9269ee0f7fd5dde3273274385645a963700b92424e63c0f232dc0fea541bcf24", "task_id": "emo_Infatuation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.021902501583099365, "target_z": -0.3261718657510402, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.7475827932357788, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/907161bceb3f5e727258e0d9.mp3" }, { "key": "original-emo_Infatuation-de-1-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "3e74fde44d4a99754d8175801796c1bac598055c6e72697114a1805ec17488d3", "task_id": "emo_Infatuation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.5161080956459045, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/306852aad2c2837cf5efff4a.mp3" }, { "key": "original-emo_Infatuation-de-1-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "ef9788c47e19f2697ed91fc6c1d637c62509502b4a2c40179ec9e1dfecce8506", "task_id": "emo_Infatuation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.01509597897529602, "target_z": -0.39453125645276266, "ce": 6.372091293334961, "genuineness": 4.15588903427124, "identity": 0.5683853626251221, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/4e6243767607aa2da9d621f2.mp3" }, { "key": "original-emo_Infatuation-de-1-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "972fb33184dabad0ef007de39f72218fb854ec06345c7d34c25d33dbdaaf0ac2", "task_id": "emo_Infatuation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.009217306971549988, "target_z": -0.3496093734943554, "ce": 6.284721851348877, "genuineness": 4.21237325668335, "identity": 0.5507599711418152, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/57678ab31c84bbb4faf516a3.mp3" }, { "key": "original-emo_Infatuation-de-1-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "b378e42c60ebece8515e34425988c64c7ff74262b7037fb653a4109cd470f768", "task_id": "emo_Infatuation-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.0620722621679306, "target_z": -0.2519531325282231, "ce": 6.292664527893066, "genuineness": 4.419482707977295, "identity": 0.5529632568359375, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/de/882d9c13b51f07036059263c.mp3" }, { "key": "original-emo_Infatuation-en-0-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "bb74f1f1a1cd2da3e87dda9b2c9e1b5a147dd803e66d2caf659435371d6ada23", "task_id": "emo_Infatuation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.08110005408525467, "target_z": -0.2167968709132503, "ce": 6.229123115539551, "genuineness": 4.319066047668457, "identity": 0.5601055026054382, "hypothesis": "The 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_Infatuation/en/952b338064ff75407c90023f.mp3" }, { "key": "original-emo_Infatuation-en-0-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "d7457ba7664afaa7f44370d9ad63e1ac7c969b8770f3e26a15f367f4bb7729df", "task_id": "emo_Infatuation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.14109042286872864, "target_z": -0.10595704732813364, "ce": 6.252951145172119, "genuineness": 4.118232727050781, "identity": 0.46547573804855347, "hypothesis": "The 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_Infatuation/en/163a8b1bf3d90638251e9302.mp3" }, { "key": "original-emo_Infatuation-en-0-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "2a417a6de64f82c752cb5e93729074d2183b9112690f8522c9b1edd2bc1ce123", "task_id": "emo_Infatuation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.08374279737472534, "target_z": -0.2119140671244799, "ce": 6.1894097328186035, "genuineness": 4.20609712600708, "identity": 0.35329049825668335, "hypothesis": "The 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_Infatuation/en/6b4d5542dc6e424aa2dc87f8.mp3" }, { "key": "original-emo_Infatuation-en-0-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "75014e6ffb5a0c62cf1ee844ed23898f2061f93be16c250619944a84f07cc3bd", "task_id": "emo_Infatuation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.002874717116355896, "target_z": -0.3613281136001193, "ce": 6.252951145172119, "genuineness": 3.9550557136535645, "identity": 0.49619045853614807, "hypothesis": "The 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_Infatuation/en/fe7ce6a11ae2f6131dce9a55.mp3" }, { "key": "original-emo_Infatuation-en-0-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "be1f0d66ade1eca90bd8fc7472088a979c0008aeda41e1b32182e2df583c3df2", "task_id": "emo_Infatuation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.0314163863658905, "target_z": -0.3085937555923943, "ce": 6.165581703186035, "genuineness": 4.093128204345703, "identity": 0.25199970602989197, "hypothesis": "The 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_Infatuation/en/040aa15918142606634c15ba.mp3" }, { "key": "original-emo_Infatuation-en-0-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "65e22e122af330a0330cc139f47929764118ab30e3b011fb6e8de05b77306e34", "task_id": "emo_Infatuation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.019788295030593872, "target_z": -0.3300781308074864, "ce": 6.24500846862793, "genuineness": 4.13078498840332, "identity": 0.20392677187919617, "hypothesis": "The 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_Infatuation/en/f9da8dc274722cfe904f8c64.mp3" }, { "key": "original-emo_Infatuation-en-0-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "8260bd2bf7a8b7897cb2c5a5e09d7f861caaf3dc11516e8c89ceb1d571cd3d7b", "task_id": "emo_Infatuation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.04515868425369263, "target_z": -0.283203115320856, "ce": 6.213237762451172, "genuineness": 3.9927117824554443, "identity": 0.27381598949432373, "hypothesis": "The 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_Infatuation/en/cfe8f8c370c75f4a1b12ddee.mp3" }, { "key": "original-emo_Infatuation-en-0-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "cb69a849cb92b730838e73953768747a8535585e6f73067db01f5f358309c411", "task_id": "emo_Infatuation-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 6.252951145172119, "genuineness": 3.9173994064331055, "identity": 0.035350993275642395, "hypothesis": "The 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_Infatuation/en/6958c7b2cfb562821b167196.mp3" }, { "key": "original-emo_Infatuation-en-1-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "7a99374257607a8d61b4b3624fa8b40c503241957ca898c85777b6b3dcbafb3b", "task_id": "emo_Infatuation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.09008539468050003, "target_z": -0.2001953132528223, "ce": 6.3641486167907715, "genuineness": 4.444586753845215, "identity": 0.3725421726703644, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/en/4d2448d86a880723662eb652.mp3" }, { "key": "original-emo_Infatuation-en-1-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "8b0924f9a26ab2198826244fc5f4c4a22ce7ab8992972a9997fa9f1c8d04c3b3", "task_id": "emo_Infatuation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.11017028242349625, "target_z": -0.1630859328755201, "ce": 6.372091293334961, "genuineness": 4.545003414154053, "identity": 0.31081628799438477, "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_Infatuation/en/052228fb1f7a630a197637b1.mp3" }, { "key": "original-emo_Infatuation-en-1-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "e5284ebd2e7bb75542539b800c9b774278aa974e90593325ae0c6f764b3e94f6", "task_id": "emo_Infatuation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.12866951525211334, "target_z": -0.12890625129055253, "ce": 6.419747352600098, "genuineness": 4.507347106933594, "identity": 0.4320351183414459, "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_Infatuation/en/e67b456b324f42d9326229a2.mp3" }, { "key": "original-emo_Infatuation-en-1-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "5b9c1e687ccbb58df74e068e52bbdbfb5109e7a7d2a8f7d0ea1c968898d03d0e", "task_id": "emo_Infatuation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.13712631165981293, "target_z": -0.1132812461283424, "ce": 6.38003396987915, "genuineness": 4.68307638168335, "identity": 0.42530837655067444, "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_Infatuation/en/904ba9b478d52b52d069bcb5.mp3" }, { "key": "original-emo_Infatuation-en-1-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "9699fe6476af3e5476f31ace1f0e12b11968619cc7aa2c293fdb1bab89f939df", "task_id": "emo_Infatuation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.08955684304237366, "target_z": -0.20117187951693385, "ce": 6.308549880981445, "genuineness": 4.337893962860107, "identity": 0.3337039351463318, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/en/42d31c6107f3c9dceef6cdce.mp3" }, { "key": "original-emo_Infatuation-en-1-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "933bab87694a7456fc060051ef280636acbd07958af6a29f4413e1f66483b824", "task_id": "emo_Infatuation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.09748508781194687, "target_z": -0.1865234406188353, "ce": 6.260893821716309, "genuineness": 4.444586753845215, "identity": 0.2492808848619461, "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_Infatuation/en/d3b212db9a1dbb9ace523965.mp3" }, { "key": "original-emo_Infatuation-en-1-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "c9edba6f3300aac3e1f962895db5156cd5eb0d13888ca084232ae7aebe992961", "task_id": "emo_Infatuation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.12866951525211334, "target_z": -0.12890625129055253, "ce": 6.372091293334961, "genuineness": 4.494794845581055, "identity": 0.327698290348053, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/en/cc158f229395e6ffb208d0db.mp3" }, { "key": "original-emo_Infatuation-en-1-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "932cf2066ed48dc39474e383e20ff56c57b7db77dd07a5e97e190049d94d995e", "task_id": "emo_Infatuation-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.09854219108819962, "target_z": -0.18457030809061217, "ce": 6.332377910614014, "genuineness": 4.65797233581543, "identity": 0.6245707273483276, "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_Infatuation/en/fe1aa9fedbba5bc50f03af8a.mp3" }, { "key": "original-emo_Infatuation-es-0-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "eee26aab100b2827a526c25c80340e9312146706699ed9773dffbbada8e93928", "task_id": "emo_Infatuation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.011331498622894287, "target_z": -0.34570313596969654, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.561470627784729, "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_Infatuation/es/43f320fb1bc934d1a150f85b.mp3" }, { "key": "original-emo_Infatuation-es-0-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "184210c3ee422758e72c5e325ddfb4ab8ae9d34540a078c3ff67e7b43df2dbbd", "task_id": "emo_Infatuation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.011331498622894287, "target_z": -0.34570313596969654, "ce": 5.982900142669678, "genuineness": 3.798154592514038, "identity": 0.4803357720375061, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/b0540eb24dbfe2510dfcc09d.mp3" }, { "key": "original-emo_Infatuation-es-0-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "1a977b5d1a1d60aa64d1b073ff0f12f4cd4a04c7d6744bf1847eba463dc71619", "task_id": "emo_Infatuation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.011331498622894287, "target_z": -0.34570313596969654, "ce": 5.935244083404541, "genuineness": 3.6663577556610107, "identity": 0.4040735363960266, "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_Infatuation/es/7f632e39d9374788bcae2032.mp3" }, { "key": "original-emo_Infatuation-es-0-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "35baf8c3098b894ffbb92f95ac88a07f3b7a6e5520c7a79f597f05c887bdb41a", "task_id": "emo_Infatuation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.0018176138401031494, "target_z": -0.3632812461283424, "ce": 6.133810997009277, "genuineness": 4.18099308013916, "identity": 0.5169957876205444, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/26386f4a615989f68a1810fb.mp3" }, { "key": "original-emo_Infatuation-es-0-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "5266ece7c51f428679399db472b8dc8ed69920c11cb50d66cfed4dab868420b7", "task_id": "emo_Infatuation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.012388601899147034, "target_z": -0.34375000344147344, "ce": 6.252951145172119, "genuineness": 4.287685871124268, "identity": 0.48492109775543213, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/198bfab7ca87b14f5350251a.mp3" }, { "key": "original-emo_Infatuation-es-0-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "c95d39b9c63d9912ebe474bc367ce9d7429f6aafc9c19474c158c703cce96d0b", "task_id": "emo_Infatuation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.01721017062664032, "target_z": -0.3984374939774215, "ce": 6.022613525390625, "genuineness": 4.2374773025512695, "identity": 0.5329869389533997, "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_Infatuation/es/fc74eb89c0fcdbe395e11108.mp3" }, { "key": "original-emo_Infatuation-es-0-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "11399204dda8fdb4615ffb65ce5b77ec3613d6a84e3313eb4b7403d1a87c3bcb", "task_id": "emo_Infatuation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 6.165581703186035, "genuineness": 4.281409740447998, "identity": 0.4168204069137573, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/90767114c48602cdd68fa444.mp3" }, { "key": "original-emo_Infatuation-es-0-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "3ff134c7254514f8051bdfc619bbf8867206ff10e8d6c68df85256419b01be58", "task_id": "emo_Infatuation-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.02084539830684662, "target_z": -0.3281249982792633, "ce": 5.974957466125488, "genuineness": 4.124508857727051, "identity": 0.6133662462234497, "hypothesis": "la puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/2b89b977a356f83eb061dfb1.mp3" }, { "key": "original-emo_Infatuation-es-1-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "cd6ecd9c41d96e92218e8472e2a7cec64d4cbff12c2e753469aa684d2ace5e8a", "task_id": "emo_Infatuation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.016617000102996826, "target_z": -0.33593750086036833, "ce": 6.078212261199951, "genuineness": 4.394378662109375, "identity": 0.6441125869750977, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/629f90174840e2c32180bafd.mp3" }, { "key": "original-emo_Infatuation-es-1-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "64e45c932c63b221e8491ac3003b8b12440374c818b7661b6f55187e7a67abad", "task_id": "emo_Infatuation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.04621577262878418, "target_z": -0.28125001032442026, "ce": 6.038498878479004, "genuineness": 4.400654315948486, "identity": 0.7744705677032471, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/cccd68728efee7870a366b99.mp3" }, { "key": "original-emo_Infatuation-es-1-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "1e8c5e127b050ee0cd982d752111e4f7824b1a6506b189a0d508f570e1e8b462", "task_id": "emo_Infatuation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.0013536810874938965, "target_z": -0.36914061618122435, "ce": 6.086154937744141, "genuineness": 4.770940780639648, "identity": 0.6665342450141907, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/2b3fda326f6255db611a88ea.mp3" }, { "key": "original-emo_Infatuation-es-1-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "d65039c2ff2beac046fcda3b6656b1010b6803304cc4b03ccb2024e163970fac", "task_id": "emo_Infatuation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.02507379651069641, "target_z": -0.32031249569815823, "ce": 5.8875885009765625, "genuineness": 4.469690799713135, "identity": 0.7304875254631042, "hypothesis": "He encontrado la cajita. estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/8e66240463409397fee9e337.mp3" }, { "key": "original-emo_Infatuation-es-1-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "0f23454ca277c9a7b78b4360f75bf96a6d2daa8ab113930e1e8b728208839ed9", "task_id": "emo_Infatuation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.016617000102996826, "target_z": -0.33593750086036833, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.7429739236831665, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/8b3bb7ea43a053680e06dc90.mp3" }, { "key": "original-emo_Infatuation-es-1-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "f662ff721d8ec636bd5c7655c22c22cc63e3b1ced57238e7b8fcd067dbe5f9a4", "task_id": "emo_Infatuation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.003931805491447449, "target_z": -0.35937500860368354, "ce": 6.022613525390625, "genuineness": 4.7834930419921875, "identity": 0.7455872297286987, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/f52ca05bee95f18d7947ab37.mp3" }, { "key": "original-emo_Infatuation-es-1-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "2abde9942ebc587f6461bf133dbcce7ad3dddfef5d0db1239720ac017cd8b933", "task_id": "emo_Infatuation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.008160203695297241, "target_z": -0.3515625060225785, "ce": 6.133810997009277, "genuineness": 4.557555198669434, "identity": 0.6085432767868042, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/db8a3fcd586007d9230c584a.mp3" }, { "key": "original-emo_Infatuation-es-1-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "8578c28d7eb1f900d98aeac0b354d341cda42fa92966f5b799820347ebc8cfe6", "task_id": "emo_Infatuation-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.009217306971549988, "target_z": -0.3496093734943554, "ce": 6.181467056274414, "genuineness": 4.7081804275512695, "identity": 0.6867810487747192, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/es/fbca2361e8f6e0ca62fffd13.mp3" }, { "key": "original-emo_Infatuation-fr-0-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "2984d79136df76057bdd216d2ce5491a32c38ea52ac45bbd5a547656b933c218", "task_id": "emo_Infatuation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.002410784363746643, "target_z": -0.37109374870944745, "ce": 6.165581703186035, "genuineness": 4.494794845581055, "identity": 0.7793756723403931, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/3ec659a885f661a6b2f4ee76.mp3" }, { "key": "original-emo_Infatuation-fr-0-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "cfed79cd7d2a082e39ea6ff7e8137df2f84647769b2955bde5712695a93b5de8", "task_id": "emo_Infatuation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.010274410247802734, "target_z": -0.3476562409661323, "ce": 6.133810997009277, "genuineness": 4.3127899169921875, "identity": 0.7342425584793091, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/6ce05efcf7b5ffd9580dd351.mp3" }, { "key": "original-emo_Infatuation-fr-0-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "f0091055810202de5dd96272c1e8f01d6939abfe7fb71bbda3aece9c0e37f7f9", "task_id": "emo_Infatuation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.00029659271240234375, "target_z": -0.3671875111847886, "ce": 6.165581703186035, "genuineness": 4.482243061065674, "identity": 0.6428765058517456, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/fe44ed4c10e335640eeb0905.mp3" }, { "key": "original-emo_Infatuation-fr-0-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "c34e34fe4e24b45cc85c1280f3670d9711f1773e30aabad93958f0356af43174", "task_id": "emo_Infatuation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.025666967034339905, "target_z": -0.41406249913963167, "ce": 6.125868320465088, "genuineness": 4.193545341491699, "identity": 0.7857251167297363, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/c492940c47ba4e7e3c448590.mp3" }, { "key": "original-emo_Infatuation-fr-0-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "6068d097b9a64c17551e67a66554e669cbd766dd639f74547d9dac99678eee88", "task_id": "emo_Infatuation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 6.141753673553467, "genuineness": 4.632867813110352, "identity": 0.6297760009765625, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/17c74450decd2360d957390e.mp3" }, { "key": "original-emo_Infatuation-fr-0-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "9fce884f97b0f6b3b820d3a56b11462b203e477c4ea17e8afd25db0ed81204bd", "task_id": "emo_Infatuation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 6.109982967376709, "genuineness": 4.394378662109375, "identity": 0.5935199856758118, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/b6bcbf15ada9f81182e33c30.mp3" }, { "key": "original-emo_Infatuation-fr-0-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "fb69ddbbeb69543d13f876323ba3a37bdc25426f1d732f3d8812de2bfcafa390", "task_id": "emo_Infatuation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": -0.007696285843849182, "target_z": -0.38085938381877565, "ce": 6.062326908111572, "genuineness": 4.394378662109375, "identity": 0.7698971033096313, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/352bd76c1b7c649a4e9c9231.mp3" }, { "key": "original-emo_Infatuation-fr-0-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "b438cb4c243e6deaa1d53ea5184fffa1ec3f30ff0895217f10d79dce5f7fec12", "task_id": "emo_Infatuation-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.007103100419044495, "target_z": -0.3535156385508016, "ce": 6.070269584655762, "genuineness": 4.595211505889893, "identity": 0.6559531092643738, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/c5f143bf70a2db432c90cf36.mp3" }, { "key": "original-emo_Infatuation-fr-1-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "24dc3cdee1c908c516573dd924034b37c392cee55ca24cef0f233b1b8d994175", "task_id": "emo_Infatuation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.07581455260515213, "target_z": -0.2265625060225785, "ce": 6.046441555023193, "genuineness": 4.482243061065674, "identity": 0.7290235757827759, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/aa33f4602367bf274ba49b85.mp3" }, { "key": "original-emo_Infatuation-fr-1-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "9e66b21a00f3750b0ce17436721dd94884f608274e17aa18d3009598b38d6f0c", "task_id": "emo_Infatuation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.07105760276317596, "target_z": -0.23535157486779512, "ce": 6.117925643920898, "genuineness": 4.557555198669434, "identity": 0.6982181072235107, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/3aca05cde55d2a25ea4b9d0a.mp3" }, { "key": "original-emo_Infatuation-fr-1-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "aadf34235977dcfb517299f17aaa91388c1367581e5dfe40ba8b853041882d38", "task_id": "emo_Infatuation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.07581455260515213, "target_z": -0.2265625060225785, "ce": 5.990842819213867, "genuineness": 4.582659721374512, "identity": 0.8322924375534058, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/befa8af76b30f5e4cd14c895.mp3" }, { "key": "original-emo_Infatuation-fr-1-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "617da45dbb2b86098d69aab418750326584cceb9acf2d5a896cfb2200a0c0ff0", "task_id": "emo_Infatuation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.09907073527574539, "target_z": -0.1835937555923943, "ce": 6.149696350097656, "genuineness": 4.607763767242432, "identity": 0.5855928659439087, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/7aebacdaafc927eaf4bc4e1a.mp3" }, { "key": "original-emo_Infatuation-fr-1-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "13fe5d507f5d5a81a692edee84ba476a8ce34e414ac59bb38237ba2741fced95", "task_id": "emo_Infatuation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.07422890514135361, "target_z": -0.22949219104901947, "ce": 6.252951145172119, "genuineness": 4.7458367347717285, "identity": 0.8342400193214417, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/bc40f0fab30a6a89592ea59b.mp3" }, { "key": "original-emo_Infatuation-fr-1-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "3e7981eb37f9cd168ccafe18659de921323d8af19fdba890d874eda2690361c0", "task_id": "emo_Infatuation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.08321425318717957, "target_z": -0.21289061962269779, "ce": 6.181467056274414, "genuineness": 4.243753433227539, "identity": 0.7220200896263123, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/77a57d15379d54ce853473d7.mp3" }, { "key": "original-emo_Infatuation-fr-1-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "f5622e556eeefebbc462b795875995aac37be4fda658ba47505bd5146db612b4", "task_id": "emo_Infatuation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.0641864687204361, "target_z": -0.2480468674717769, "ce": 6.23706579208374, "genuineness": 4.570107460021973, "identity": 0.596771240234375, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/51111702bc271fa7f47782f7.mp3" }, { "key": "original-emo_Infatuation-fr-1-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "4a4f75c93f398f77c00b24bca51e30e24dbc7e91ff6200e06f4f6dcb3e84089a", "task_id": "emo_Infatuation-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.0784573033452034, "target_z": -0.2216796884679144, "ce": 6.09409761428833, "genuineness": 3.9676074981689453, "identity": 0.7575916051864624, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/fr/9a5b382454a5543b179c68c7.mp3" }, { "key": "original-emo_Infatuation-nl-0-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "fd04d904968d5705ba7b20286a9ce49c1c97a2b3b2905185588b8c457cdd181a", "task_id": "emo_Infatuation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.03775899112224579, "target_z": -0.296874987954843, "ce": 6.109982967376709, "genuineness": 4.268857479095459, "identity": 0.5787816047668457, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/d782516394939591092fa019.mp3" }, { "key": "original-emo_Infatuation-nl-0-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "1fcfbc34fde8f7a1132f31216cb879dd46573ba01b0010478c01af69c085422c", "task_id": "emo_Infatuation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.06365790963172913, "target_z": -0.24902344750178212, "ce": 6.133810997009277, "genuineness": 4.13078498840332, "identity": 0.6203691959381104, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/e03f5a587e79becc83df16a8.mp3" }, { "key": "original-emo_Infatuation-nl-0-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "b8b3e2bfc791e4b93a71c564bd525a2796352e7709c03ee5dbc3366a00209ffd", "task_id": "emo_Infatuation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.010274410247802734, "target_z": -0.3476562409661323, "ce": 6.070269584655762, "genuineness": 4.344170093536377, "identity": 0.49712395668029785, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/e775cf014631706b272c48fc.mp3" }, { "key": "original-emo_Infatuation-nl-0-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "c0d7fb7de91e8e2c766cbe0eebfe0fd20894ea7f8b696cd98471eb6adaa03fdd", "task_id": "emo_Infatuation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.009217306971549988, "target_z": -0.3496093734943554, "ce": 6.006728172302246, "genuineness": 4.356721878051758, "identity": 0.20648804306983948, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/07d0dd2df67d381a79fd5eff.mp3" }, { "key": "original-emo_Infatuation-nl-0-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "b507d966d87890382796aacf2273a759e760ed8c8ee2bc55014a2806d0b454d7", "task_id": "emo_Infatuation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.016617000102996826, "target_z": -0.33593750086036833, "ce": 6.109982967376709, "genuineness": 4.3881025314331055, "identity": 0.6705085039138794, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/cc5ae494065b9a342623621c.mp3" }, { "key": "original-emo_Infatuation-nl-0-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "dbfac19d12d966a55f1a873203e27412f49aaf58c32ae1e121cb04a548ac9b1b", "task_id": "emo_Infatuation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.022959589958190918, "target_z": -0.32421876075460443, "ce": 5.998785495758057, "genuineness": 4.300237655639648, "identity": 0.6929778456687927, "hypothesis": "De deur staan nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/e8c28daa2b4f644c904f0d44.mp3" }, { "key": "original-emo_Infatuation-nl-0-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "7035ccaa9c0a91c337ddd380b378b1d49a37a517e0845403552c9a1330fe4e00", "task_id": "emo_Infatuation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.030359283089637756, "target_z": -0.3105468881206174, "ce": 6.165581703186035, "genuineness": 4.337893962860107, "identity": 0.5886697173118591, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/5dc9821f4000d1ba10bdece7.mp3" }, { "key": "original-emo_Infatuation-nl-0-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "f34db2b85619352161e9961e893359476af6daa7170a2e7475276703f4cb5764", "task_id": "emo_Infatuation-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.02507379651069641, "target_z": -0.32031249569815823, "ce": 6.054384231567383, "genuineness": 4.1998209953308105, "identity": 0.6636189818382263, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/dd8e2246b17c04638c158c1f.mp3" }, { "key": "original-emo_Infatuation-nl-1-seed1701-scale0.0", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "8f09c53285efa7befbbf4bc3a75cd61ab6820256e20de9171b751e479594386d", "task_id": "emo_Infatuation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.011331498622894287, "target_z": -0.34570313596969654, "ce": 5.998785495758057, "genuineness": 4.319066047668457, "identity": 0.6914952993392944, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/a4e025a05f2e7e170439ee0b.mp3" }, { "key": "original-emo_Infatuation-nl-1-seed1701-scale0.5", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "4a74f226735adf5b38632d2e1bba79d28d158372adf25857361df70ce79c8829", "task_id": "emo_Infatuation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.03458768129348755, "target_z": -0.3027343855395124, "ce": 6.149696350097656, "genuineness": 3.9927117824554443, "identity": 0.6230257749557495, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/b2f8a91b306513001cf560bb.mp3" }, { "key": "original-emo_Infatuation-nl-1-seed1701-scale0.75", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "a8e72e14cd4cc260016e77351bb5d775d1530dbe6bbfedb2a922ddc72b3c351f", "task_id": "emo_Infatuation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.0018176138401031494, "target_z": -0.3632812461283424, "ce": 6.157639026641846, "genuineness": 4.105680465698242, "identity": 0.7078564763069153, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/46b3e3c33d788d4c46944f1c.mp3" }, { "key": "original-emo_Infatuation-nl-1-seed1701-scale1.0", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "c8d54c5d9b9db60065c9467d0df7af0267397be609098ecbdab75d641d3151a1", "task_id": "emo_Infatuation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 6.1894097328186035, "genuineness": 4.519899368286133, "identity": 0.4376091957092285, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/002d81a56e228b85909473d4.mp3" }, { "key": "original-emo_Infatuation-nl-1-seed1702-scale0.0", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "71dac7af91e1b73cb679a4a70f984c58cf9d9bc936345f55f2a47b0dbb013a9e", "task_id": "emo_Infatuation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.01555989682674408, "target_z": -0.3378906333885915, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.5217994451522827, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/689bc85b300152e23fb31a5e.mp3" }, { "key": "original-emo_Infatuation-nl-1-seed1702-scale0.5", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "0a12fabeef452198be2b62ff82374c9d2b3aa7275def1bf9585a7267bb9eb93c", "task_id": "emo_Infatuation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.009217306971549988, "target_z": -0.3496093734943554, "ce": 6.078212261199951, "genuineness": 4.457139015197754, "identity": 0.6386973857879639, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/416c0f1e918ae7d621e4ead9.mp3" }, { "key": "original-emo_Infatuation-nl-1-seed1702-scale0.75", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "d74ccb7e1cafc4cb3c30cd2317486e903886227ad520a5994de479531d50f8a7", "task_id": "emo_Infatuation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.026130899786949158, "target_z": -0.31835936316993513, "ce": 6.125868320465088, "genuineness": 4.193545341491699, "identity": 0.4516274929046631, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/cc568280661ba610c89163a7.mp3" }, { "key": "original-emo_Infatuation-nl-1-seed1702-scale1.0", "bucket": "emo_Infatuation", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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 Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "5acce02f0260faf6e2b4c5760b9f18361aafc75918a59a9d5992c6648750c867", "mp3_sha256": "ef82e26200d63d79063a9179969128fd3fd107eb4200db36ba63faf914950b5a", "task_id": "emo_Infatuation-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Infatuation. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Infatuation. 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 Infatuation. 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 Infatuation. 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": 0.03670188784599304, "target_z": -0.2988281204830661, "ce": 6.149696350097656, "genuineness": 4.3127899169921875, "identity": 0.4505971670150757, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Infatuation/nl/aa3078fb4c00b45bb4980177.mp3" } ], "source_standard_audio_unchanged": true }